pr-description
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from git logs and repository diffs to generate PR descriptions.
- Ingestion points: Data enters the agent context via
gh pr diffandgit logcommands as specified in the Workflow section ofSKILL.md. - Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the diff content, which could lead to the agent following malicious instructions hidden in code comments.
- Capability inventory: The skill can write files to the
/tmpdirectory and modify external GitHub Pull Requests using thegh pr editcommand. - Sanitization: No input validation, escaping, or filtering is applied to the retrieved git context before it is processed by the model.
Audit Metadata