marketing-science
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious code, obfuscated commands, or suspicious network behaviors were detected. The skill is entirely instructional and serves a legitimate academic purpose for venue selection and manuscript framing.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) because its primary function is to process and analyze untrusted user-provided manuscripts. 1. Ingestion points: User research papers and manuscript drafts ingested via the conversation context. 2. Boundary markers: The skill does not define strict delimiters for user input, though it includes a safety instruction that official journal guidelines override the skill's advice. 3. Capability inventory: The instructions suggest using external web search tools to verify live guidelines and reading local reference files at ../../resources/source-basis.md and ../../resources/official-source-map.md. 4. Sanitization: There is no evidence of input validation or sanitization of the provided manuscript content.
Audit Metadata