cold-email
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists exclusively of Markdown files providing copywriting frameworks and benchmarks.
- [DATA_EXPOSURE]: The skill instructs the agent to read context from specific workspace files (.agents/product-marketing-context.md), which is part of the intended workflow and does not target system secrets.
- [INDIRECT_PROMPT_INJECTION]: The agent is instructed to ingest external data such as LinkedIn posts or company news provided by the user. While this creates a potential surface for indirect prompt injection, the skill lacks any capabilities (network, shell, file writes) to facilitate an attack.
- Ingestion points: SKILL.md (User-provided research signals).
- Boundary markers: Absent.
- Capability inventory: None. No scripts or executable actions are defined in this skill.
- Sanitization: Absent.
Audit Metadata