code-review
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (
git diff,git log,git rev-parse) by incorporating user-supplied input (fixed-point) directly into the command string. This creates a surface for command injection if the underlying shell tool does not perform adequate sanitization of the user input. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted data from the repository, including git diffs, commit messages, and external specification files. An attacker could embed malicious instructions in these files (e.g., within code comments or commit descriptions) to manipulate the behavior of the parallel sub-agents during the review process.
- Ingestion points: Git diff output, git log/commit messages, and local repository files (e.g.,
docs/,specs/,CONTRIBUTING.md). - Boundary markers: The skill does not define explicit delimiters or instructions for the sub-agents to ignore embedded commands within the analyzed data.
- Capability inventory: The skill can execute git commands and read files from the local filesystem.
- Sanitization: No sanitization, escaping, or filtering of the ingested repository content is performed before passing it to the sub-agent prompts.
Audit Metadata