skill-seekers
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
skill-seekersPython package from a non-trusted source via pip. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from untrusted external sources, creating an attack surface where malicious instructions could be embedded in the source material.
- Ingestion points: Documentation URLs, GitHub repositories, local codebases, and PDF files processed by the
skill-seekers create,analyze, andpdfcommands. - Boundary markers: The skill does not explicitly define delimiters or instructions to prevent the agent from obeying prompts found within the processed documentation or files.
- Capability inventory: The agent uses the
skill-seekersCLI to perform scraping, analysis, and packaging, which involves file system writes and network access. - Sanitization: No evidence of sanitization or validation of the ingested content is provided in the skill instructions.
- [COMMAND_EXECUTION]: The skill relies on the execution of multiple CLI commands (
skill-seekers create,enhance,package,install,github,analyze,pdf,unified) to perform its functions.
Audit Metadata