psychological-trigger-marketing
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided marketing details which could theoretically contain malicious instructions. However, the risk is negligible as the skill lacks network or system access capabilities.\n
- Ingestion points: Workflow steps in
SKILL.mdprocess user inputs likeproduct_or_offerandtarget_audienceto generate copy directions.\n - Boundary markers: Absent; user input is processed directly within the instructional flow without specialized delimiters.\n
- Capability inventory: The skill is restricted to text generation; it does not utilize shell commands, file system access, or external network calls.\n
- Sanitization: Absent; the skill relies on the underlying model's safety guardrails to handle potentially malicious embedded content.
Audit Metadata