extract
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local Python script
extractor.pylocated within the plugin's root directory to perform AST extraction on a user-specified path. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted codebase data, which creates a vulnerability to instructions embedded in that data.
- Ingestion points: Code files located in the user-provided or current working directory (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or warnings to the agent to disregard instructions that might be embedded within code comments or string literals during the AI enrichment phase.
- Capability inventory: The skill has the capability to execute shell commands via
python3to run the extraction script (SKILL.md). - Sanitization: No sanitization, validation, or escaping of the extracted code content is specified before the AI processes it for natural language explanation.
Audit Metadata