blog-analyze
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted content from external URLs and local files, which presents a surface for indirect prompt injection attacks.
- Ingestion points: The skill reads local files and fetches external content via WebFetch as defined in the Input Handling section of SKILL.md.
- Boundary markers: No specific delimiters or instructions are provided to ensure the agent ignores embedded instructions within the blog content.
- Capability inventory: The skill possesses file reading, directory scanning, and network capabilities, and refers to a file-writing command ($blog rewrite).
- Sanitization: The skill does not implement sanitization or validation for the content it processes.
Audit Metadata