skill-lookup
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to create directories and write files, including executable scripts (Python, shell) and configurations, to the local filesystem at
.claude/skills/{slug}/. - [EXTERNAL_DOWNLOADS]: Fetches skill metadata and file contents from the
prompts.chatMCP server using thesearch_skillsandget_skilltools. - [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests untrusted content (skill files and descriptions) from an external service and writes it directly to the local environment without explicit verification or sanitization instructions.
- Ingestion points: Content returned by the
get_skilltool from the prompts.chat API. - Boundary markers: None identified; instructions do not advise the agent to verify the safety or integrity of the downloaded skill content.
- Capability inventory: File writing to the local filesystem (
.claude/skills/). - Sanitization: None identified.
Audit Metadata