apostle-article-research
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions focus on methodological rigor for research and intellectual honesty. No malicious patterns or behaviors were detected in the skill logic or instructions.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and process untrusted external data (user-supplied materials and research findings). This is a functional requirement for its stated purpose.
- Ingestion points: The "Contact the Object" section of
SKILL.mdinstructs the agent to read existing drafts and supplied materials. - Boundary markers: The skill does not define specific delimiters or instructions to ignore malicious instructions within the processed data.
- Capability inventory: The agent performs synthesis and structural revision based on the ingested content.
- Sanitization: No explicit sanitization or filtering of external content is described.
Audit Metadata