skillsmith
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external 'SKILL.md' files and associated reference documents during its audit workflow. This creates a potential vulnerability where malicious instructions embedded in the documents being audited could attempt to manipulate the agent's behavior. \n
- Ingestion points: Target skill files and associated local reference files (Audit Branch, Step 1). \n
- Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the agent from accidentally executing instructions found within the audited text. \n
- Capability inventory: The skill utilizes filesystem access for discovery (Step 1) and file creation (Step 5). \n
- Sanitization: There is no evidence of input validation or content sanitization for the files being processed. \n- [COMMAND_EXECUTION]: The skill commands the agent to perform filesystem operations to identify repository conventions and write finalized drafts. These operations are essential to the tool's function as a developer utility and are designed to occur with user oversight and confirmation.
Audit Metadata