skills/astro-han/skills/pr-review/Gen Agent Trust Hub

pr-review

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted data from pull requests, which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The skill instructions in SKILL.md require the agent to read external patches, snapshots, issue links, and repository rules.
  • Boundary markers: There are no instructions providing explicit delimiters (like XML tags or triple quotes) or warnings to ignore potentially malicious instructions embedded within the PR content.
  • Capability inventory: The skill is primarily analytical and does not explicitly request dangerous tools, subprocess execution, or network operations, though it operates within the agent's general execution environment.
  • Sanitization: The instructions do not mention any sanitization, filtering, or validation of the external text or code being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 04:33 PM
Security Audit — agent-trust-hub — pr-review