agent · ai security

Superagent

superagent.shevidence retrieved Aug 4, 2026 – Aug 18, 2026view as JSON all ai security entries 9 alternatives

Indexed12 or more fields evidenced; not yet scored by a human against the rubric

14 fields evidenced · 41 with no public information. Every value below links to the document it came from and the date we checked it.

9 of those are quoted but not yet interpreted: we hold the source sentence and the date we read it, but nobody has written the answer to the question yet. Those rows show the quote and say so rather than repeating it back as an answer. Why these exist

8 of the evidenced values quote wording our own later capture of the same page no longer contains. Marked below, awaiting an editor.

Also appears in

AI agents that support the Model Context Protocol Open-source AI agents

Trust gap

How this is scored

These scores are automated. A 1 or 2 counts how many fields this entry answers with a citation — not what those answers say. A 0 means every field for that dimension is recorded as undisclosed and none of the pages we captured mentions it. No one has scored this entry against the rubric yet.

Runtime governance

1/3 auto

Are scope, spend, and authority enforced while the agent runs?

Scored from 1 evidenced field(s): runtime_governance. Automated score; capped at 2 pending review.

Counts Runtime governance, each cited below.

Audit trail

unscored

Is there a tamper-evident record of what it actually did?

Compliance

unscored

Are compliance obligations attached per engagement?

Outcome settlement

unscored

Does payment depend on a verified result?

Insurance & indemnity

unscored

Can the deployment be insured, and is the customer indemnified?

Assurance

Insurance available: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Insurance carriers: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Coverage limits: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Indemnification: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Liability cap: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Audit trail: no public information
superagent.sh · checked Aug 18, 2026 · source did not state this
Tamper-evident log: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Explainability: not yet interpreted
“findings on the exact line, fixes as pull requests.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
superagent.sh · checked Aug 4, 2026
Runtime governance: runtime guardrails: deterministic rules that decide what your agent may do
“runtime guardrails deterministic rules that decide what your agent may do.”
superagent.sh · checked Aug 18, 2026
Permission scopes: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Compliance certifications: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Regulatory alignment: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Outcome-based pricing: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Settlement mechanism: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Dispute process: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
SLA terms: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Evaluation coverage: not yet interpreted
“self-serve red teaming against what you actually run.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
superagent.sh · checked Aug 4, 2026

Agency

Autonomy level: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Human oversight: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Goal complexity: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Action space: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Operating environment: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Initiative: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this

Safety

Safety evaluations: not yet interpreted
“self-serve red teaming against what you actually run.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
superagent.sh · checked Aug 4, 2026
Red teaming: not yet interpreted
“self-serve red teaming against what you actually run.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
superagent.sh · checked Aug 4, 2026
Safety policy: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Usage restrictions: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Model or system card: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Incident reporting: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Third-party evaluations: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Data handling: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this

Practicality

Pricing model: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Price point: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Availability: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Deployment options: not yet interpreted
“you already work in your coding agent and github. so that's where superagent works too — no new workflows or tools to learn.”
superagent.sh · checked Aug 4, 2026
Integrations: not yet interpreted
“connect to github — keeps your repos secure”
superagent.sh · checked Aug 4, 2026
Supported regions: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Support model: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this

Foundation models

Base models: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Model provider: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Model swappable: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Open weights: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Fine-tuning: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Context window: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this

Ecosystem

Protocols supported: Ships MCP-related capability: a "contributor trust" API and MCP integration (per product changelog, 2026-08-11).
“contributor trust api and mcp”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
superagent.sh · checked Aug 18, 2026
Tool use: Deterministic runtime rules govern what agents may do; sensitive activity is confined to the endpoint
“control it where it runs deterministic rules for what agents do, trust scores for everything they consume — and sensitive activity stays on the endpoint.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
superagent.sh · checked Aug 18, 2026
Multi-agent: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
API access: Contributor Trust API and MCP integration shipped per product changelog (2026-08-11); no separate REST/webhooks API documented on current homepage.
“contributor trust api and mcp”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
superagent.sh · checked Aug 18, 2026
Open source: not yet interpreted
“free for open source.”
superagent.sh · checked Aug 4, 2026
Marketplace presence: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this

Impact

User base: ubicloud, evry health, dotenvx, firecrawl, capchase, nango, mastra, paperclip
“ubicloud evry health dotenvx firecrawl capchase nango mastra paperclip”
superagent.sh · checked Aug 4, 2026
Deployment scale: not yet interpreted
“free for open source. the whole suite, on any public repo. private repos are paid — contact us and we'll set you up.”
Not in our latest capture. This quote was on the page when we filed it. We captured the same page again on Sep 16, 2026 and it was not there. The value above has not been re-checked by an editor yet. How we re-check citations
superagent.sh · checked Aug 4, 2026
Target sectors: not yet interpreted
“Security for AI-native developers”
superagent.sh · checked Aug 4, 2026
High-risk domains: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this
Documented incidents: no public information
superagent.sh · checked Aug 4, 2026 · source did not state this

Compared with

Side-by-side on the fields where Superagent and the other entry are both on record and actually differ.