marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized operations were detected in the skill's files. The skill operates as an informational assistant for marketing tasks.
- [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface by instructing the agent to read external context files. 1. Ingestion points: Local files such as .agents/product-marketing.md and .claude/product-marketing.md are read to provide context. 2. Boundary markers: Absent; the instructions do not define delimiters or specific warnings for the ingested content. 3. Capability inventory: None; the skill does not use network tools, shell execution, or file write operations. 4. Sanitization: Absent; the content of the context files is not validated or sanitized before being processed by the agent.
Audit Metadata