content-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and templates for content creation. No malicious code, prompt injections, or unauthorized data access patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external content (researching topics from the web or reviewing user drafts), which is an inherent risk factor for content processing. 1. Ingestion points: Untrusted data enters the agent context via web research sources (RSS, search) in Stage 1 and user-provided drafts in Stage 2. 2. Boundary markers: No explicit delimiters or boundary markers are used to isolate external content. 3. Capability inventory: No file-write, subprocess calls, or network operations are defined within the skill. 4. Sanitization: No sanitization or validation of ingested content is mentioned. The risk is minimized as the skill lacks high-privilege capabilities.
Audit Metadata