cartographer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local Python script
scripts/project_ops/cartographer.pyusingpython3. This is the core functional component used to perform the repository mapping. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its data processing flow.
- Ingestion points: The skill ingests the file structure and potentially the content of the target repository to generate documentation artifacts.
- Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore potentially malicious instructions embedded in the file names or content it scans.
- Capability inventory: The skill has the capability to execute shell commands (
python3) and write to the filesystem (Tree.txtanddocs/PROJECT_MAP.md). - Sanitization: There is no mention of sanitization or filtering logic in the instructions to handle adversarial data found in the repository during the mapping process.
Audit Metadata