skill-map
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires and executes the
ai-skilletCLI tool (specificallyai-skillet map) with various arguments derived from user input or agent discovery.\n- [INDIRECT_PROMPT_INJECTION]: The skill scans local files and can include snippets of their content in its output via the--include-snippetsflag. This represents a vulnerability surface where malicious instructions embedded in local files could be ingested and acted upon by the agent.\n - Ingestion points: The output of
ai-skillet mapis read by the agent, potentially including raw text from various local files.\n - Boundary markers: The instructions do not specify clear delimiters or 'ignore' instructions for the content of the matched snippets to prevent the agent from following instructions found within them.\n
- Capability inventory: The agent has the capability to execute shell commands and read wide areas of the local filesystem (defaulting to the home directory).\n
- Sanitization: There are no instructions for the agent or the tool to sanitize or filter the content of the snippets before they are processed.
Audit Metadata