discover-tasks
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The file contains no executable scripts, commands, or obfuscated content. All metadata and descriptions appear benign.
- [PROMPT_INJECTION]: The skill defines a workflow that processes content from external sources (GitHub, GitLab, and local files). This represents an attack surface for indirect prompt injection.
- Ingestion points: External Git repositories and local file paths (SKILL.md).
- Boundary markers: None provided in the current definition to isolate external data.
- Capability inventory: Tasks are discovered, ranked, and validated.
- Sanitization: No explicit sanitization or filtering of external content is described.
Audit Metadata