skill-finder-cn

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/search.sh executes the clawhub binary with user-provided queries. This is the intended functionality of the skill for searching the vendor's ecosystem.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
  • Ingestion points: Results from clawhub search in scripts/search.sh are ingested into the agent context.
  • Boundary markers: There are no explicit delimiters or safety instructions in the script or SKILL.md to prevent the agent from obeying instructions embedded in the metadata of discovered skills.
  • Capability inventory: The skill is explicitly designed to lead the agent toward executing clawhub install, which modifies the agent's environment by adding new executable components.
  • Sanitization: No sanitization or validation of the search results is performed before they are presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 07:54 AM