email-campaign-writer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill takes user-provided arguments (audience, offer, sequence type, action) to generate email copy. This represents a surface where instructions embedded in the input could influence agent behavior, though the risk is mitigated by the absence of dangerous tools.
- Ingestion points: User-supplied arguments defined in SKILL.md.
- Boundary markers: None present.
- Capability inventory: Restricted to 'Read' and 'Write' tools in SKILL.md.
- Sanitization: None present.
- [NO_CODE]: The skill consists entirely of Markdown instructions, YAML metadata, and a JSON configuration file. No executable scripts (.py, .js, .sh) are included or referenced.
- [SAFE]: External references to infloq.com belong to the documented author of the skill and represent standard website links with no automated data transmission or execution.
Audit Metadata