pr-draft-summary

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill executes several local git commands and a referenced shell script (find_latest_release_tag.sh) to identify changes and version tags. This is a functional requirement for analyzing the working tree and commit history.
  • Indirect Prompt Injection Surface: The skill processes repository data which could contain untrusted instructions.
  • Ingestion points: Data enters the context via git diff, git log, git status, and git ls-files as defined in SKILL.md.
  • Boundary markers: No explicit delimiters are specified for the ingested repository data.
  • Capability inventory: The skill possesses shell execution capabilities to run git commands and local scripts.
  • Sanitization: The workflow includes a step to normalize GitHub issue and PR references in the final output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 08:59 PM
Security Audit — agent-trust-hub — pr-draft-summary