context-map
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
context_scannerandscanner.py) to scan the project directory and generate metadata. This behavior is standard for the skill's primary purpose of mapping codebase context. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by scanning the user's local codebase to generate reports for the agent.
- Ingestion points: The skill scans the project root directory and its contents (
SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are defined for the generated output.
- Capability inventory: The skill uses shell execution (
python3) and file system traversal capabilities. - Sanitization: No sanitization or filtering logic is specified for the scanned content before it is presented to the agent.
Audit Metadata