chisle-review
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data in the form of source code and diffs provided by the user. This creates a surface where malicious instructions could theoretically be embedded in the reviewed code to influence the agent's behavior. However, the impact is minimal as the skill lacks capabilities like network access, file writing, or command execution that could be exploited.
- Ingestion points: The skill processes user-supplied diffs and files as indicated in the prompt instructions.
- Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the ingested code.
- Capability inventory: The skill is purely instructional and does not perform any subprocess calls, file operations, or network requests.
- Sanitization: The skill does not perform sanitization or filtering of the input code data.
Audit Metadata