acs-energy-letters
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains standard instructional content for a manuscript evaluation assistant. No security violations or suspicious patterns were identified in the prompt instructions, metadata, or logic.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided manuscript content, which constitutes an untrusted data ingestion surface. 1. Ingestion points: Manuscript text provided by the user during the agent interaction. 2. Boundary markers: The skill does not explicitly define delimiters or instructions for the agent to ignore potentially malicious instructions embedded within the user's manuscript. 3. Capability inventory: The skill instructs the agent to read local resource files (e.g., source-basis.md) and perform web searches for official journal guidelines. 4. Sanitization: There are no explicit sanitization or filtering steps for the ingested data.
Audit Metadata