llm-docs-optimizer
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local Python script
scripts/analyze_docs.pyto perform static analysis on project documentation. The script uses standard libraries (re, sys, pathlib) to parse markdown and identify formatting or content issues based on c7score metrics. It does not execute the code contained within the analyzed snippets. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted documentation files provided by the user, creating a surface where malicious instructions could be embedded in the data to be optimized.
- Ingestion points: The agent is instructed in
SKILL.mdto read README.md and other documentation files within a project directory. - Boundary markers: The instructions do not define specific delimiters or "ignore" warnings to prevent the agent from obeying instructions found within the processed documentation.
- Capability inventory: The skill possesses file read/write capabilities for optimization and shell execution for the analysis script.
- Sanitization: No explicit sanitization or filtering is performed on the ingested content beyond the structural analysis provided by the Python script.
Audit Metadata