triage-findings

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from local files and remote GitHub PRs, which serves as an entry point for instructions that could influence the agent's triage decisions.
  • Ingestion points: Instructions in SKILL.md direct the agent to load the active findings record from path/findings.md and context from an optional GitHub PR url provided in the prompt.
  • Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the content read from findings files or PR URLs.
  • Capability inventory: The results of the triage phase are used to decide the execution of subsequent tools, including scan-codebase, test-codebase, sync-findings, and resolve-findings.
  • Sanitization: There is no explicit logic for validating or escaping the content of the findings records before the agent interpolates the data into its decision-making context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 04:31 PM
Security Audit — agent-trust-hub — triage-findings