alternatives-pages
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze developer sentiment and conversations from social listening tools and forums. This creates a surface for indirect prompt injection where external content could influence the agent's research phase. \n
- Ingestion points: External data from social media and forums as described in the 'Research Developer Conversations' section. \n
- Boundary markers: No specific boundary markers or instructions to ignore embedded commands are included. \n
- Capability inventory: None. The skill does not contain executable tools or commands. \n
- Sanitization: No sanitization of external data is specified. \n- [METADATA_POISONING]: The YAML frontmatter includes a
risk: criticalfield that does not align with the instructional and benign nature of the skill content.
Audit Metadata