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.shexecutes theclawhubbinary 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 searchinscripts/search.share ingested into the agent context. - Boundary markers: There are no explicit delimiters or safety instructions in the script or
SKILL.mdto 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