hook-writing
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a structured framework for generating creative copy for advertising and social media. Analysis of the instructions and metadata revealed no malicious code, obfuscation, unauthorized network operations, or persistence mechanisms. The link provided in the documentation leads to the author's verified website (motionapp.com).
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information regarding products, personas, and messaging angles. Although this creates an input surface for potential indirect prompt injection, the risk is mitigated as the skill does not include any associated scripts, tool definitions, or file-system writing capabilities that could be abused.
- Ingestion points: Required inputs defined in SKILL.md including Product, Pain or Desire, Persona, and Awareness Stage.
- Boundary markers: The instructions do not specify any delimiters or safety boundaries for user-provided content.
- Capability inventory: No tools or scripts are defined or requested within the skill files.
- Sanitization: The skill does not implement any validation or sanitization for input data.
Audit Metadata