skills/sebas-aikon-intelligence/antigravity-awesome-skills/address-github-comments/Gen Agent Trust Hub
address-github-comments
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external GitHub pull request comments and issue feedback via the
gh pr view --commentscommand. This data is controlled by third parties and could contain instructions designed to manipulate the agent's behavior during the categorization and fix application phases. - Ingestion points:
gh pr view --commentscommand output mentioned inSKILL.md. - Boundary markers: Absent. The instructions do not specify delimiters or warnings for the agent to ignore instructions embedded within the comments.
- Capability inventory: The agent is expected to apply code changes (file system writes) and respond to threads using
gh pr comment(network operations). - Sanitization: Absent. There is no mention of filtering or validating the comment content before processing.
- [COMMAND_EXECUTION]: The skill relies on the GitHub CLI (
gh) to perform its primary functions, including viewing comments and posting responses. This involves executing shell commands which require the environment to be pre-authenticated.
Audit Metadata