hack-review
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill audits untrusted code changes from working trees, diffs, and pull requests, creating a vulnerability to indirect prompt injection attacks where malicious code could influence the agent's report findings.
- Ingestion points: The skill reads external file content, Git diffs, and pull request metadata to perform its analysis (SKILL.md).
- Boundary markers: The instructions lack specific requirements for the agent to use boundary markers or delimiters when ingesting code, nor do they instruct the agent to ignore instructions embedded within the reviewed data (SKILL.md).
- Capability inventory: The agent has the capability to execute shell commands (
git diff,git show,openssl,uuidgen) and write report files to the local file system within thetmp/directory (SKILL.md). - Sanitization: No explicit sanitization or filtering of the code content is described in the workflow before the data is processed by the agent (SKILL.md).
Audit Metadata