manage-knowhow-capture

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute system commands, specifically curl, to fetch content for the reference knowledge type.
  • [EXTERNAL_DOWNLOADS]: The reference capture mode (Step 3) downloads content from arbitrary user-provided URLs via the --source flag.
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it ingests and processes untrusted data from external websites.
  • Ingestion points: External content is fetched from URLs provided in the $ARGUMENTS through the --source flag (SKILL.md).
  • Boundary markers: The instructions do not specify any delimiters or warnings (e.g., "ignore embedded instructions") to isolate the fetched content from the agent's control flow.
  • Capability inventory: The skill possesses Bash execution, Write access to the filesystem, and the ability to interact with the user via request_user_input (SKILL.md).
  • Sanitization: There is no mention of sanitization, validation, or escaping of the content fetched via curl before the agent extracts key points from it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 08:44 AM
Security Audit — agent-trust-hub — manage-knowhow-capture