skills/agentskillexchange/skills/Package docs, repos, and PDFs into installable agent skills with Skill Seekers/Gen Agent Trust Hub
Package docs, repos, and PDFs into installable agent skills with Skill Seekers
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process data from external, untrusted sources including documentation websites, GitHub repositories, and PDF files. This creates a potential surface for indirect prompt injection, where an attacker could place malicious instructions inside a public documentation site or repository that the agent might inadvertently follow when packaging the content.
- Ingestion points: Accepts external URLs (e.g., docs.django.com), GitHub repositories, and PDF files.
- Boundary markers: The provided instructions do not specify any delimiters or safety markers to differentiate between instructions and the untrusted content being processed.
- Capability inventory: The
skill-seekers createcommand facilitates the creation of new agent packages and supports an--agent-cmdflag for specifying execution commands. - Sanitization: There are no explicit instructions for sanitizing or filtering the content fetched from external sources before processing.
- [EXTERNAL_DOWNLOADS]: The installation section directs users to install the
skill-seekerspackage and its variants (gemini, openai, minimax, video) from PyPI. This is standard behavior for a CLI tool integration and uses official package management channels.
Audit Metadata