clean-comments
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from source code files and a local rules file, which presents a surface for instructions embedded in data.
- Ingestion points: Reads local code files (with extensions like .go, .ts, .py) and the file
~/.claude/rules/comments.mdin SKILL.md. - Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are provided in the workflow.
- Capability inventory: The skill has the ability to read and write local files, and execute git commands (
git diff,git add) in SKILL.md. - Sanitization: There is no evidence of sanitization or escaping of the content read from files before it is processed by the model.
- [COMMAND_EXECUTION]: The skill interacts with the local environment using standard git commands to identify and stage modified files.
- Evidence: The workflow utilizes
git diff --cached --name-only --diff-filter=ACMto retrieve staged files andgit add <file>to re-stage them after processing in SKILL.md.
Audit Metadata