find-tool
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for identifying and recommending third-party packages and tools from public registries such as npm, PyPI, and crates.io. It directs the agent to provide exact installation commands to the user, acting as a gateway for external software acquisition.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes content from untrusted external sources like package descriptions and search results.\n
- Ingestion points: The agent retrieves data from web searches, package registry metadata, and GitHub repository content (Workflow Step 3).\n
- Boundary markers: The instructions do not mandate the use of delimiters or 'ignore' warnings for the ingested external data.\n
- Capability inventory: The skill influences the agent to generate installation commands for the user, which is the primary capability that could be exploited via malicious external data.\n
- Sanitization: No specific sanitization or filtering steps are required for the retrieved content before it is presented or used for decision-making.\n- [NO_CODE]: The skill contains only instructional Markdown and YAML configuration; it does not include any executable scripts, binaries, or active code components.
Audit Metadata