pr-threads-address

Warn

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill attempts to install a third-party GitHub CLI extension agynio/gh-pr-review if it is not already present on the system.
  • [COMMAND_EXECUTION]: The skill relies on the gh command-line tool and the gh-pr-review extension to perform various operations including viewing PR details, repository metadata, and managing review threads.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon pull request comments and review feedback, which are often provided by external contributors.
  • Ingestion points: The agent fetches unresolved PR review threads and comments using the gh pr-review review view command as specified in SKILL.md.
  • Boundary markers: There are no explicit instructions or delimiters provided to the agent to distinguish between legitimate feedback and potentially malicious instructions embedded within the PR comments.
  • Capability inventory: The agent is authorized to perform code modifications, execute tests, commit changes to the repository, and post replies to GitHub threads.
  • Sanitization: The skill does not specify any sanitization, validation, or filtering of the comment content before the agent analyzes and implements the requested changes.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 14, 2026, 02:37 PM
Security Audit — agent-trust-hub — pr-threads-address