icp-persona
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed exclusively of Markdown instructions and static reference documents. No executable scripts (.py, .js, .sh), binaries, or package manager configuration files (requirements.txt, package.json) are included or referenced.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided context regarding products, industries, and audiences to populate marketing templates, which represents a standard indirect injection surface. However, the lack of dangerous capabilities mitigates this risk.
- Ingestion points: User-provided inputs defined in
SKILL.md(Product/service name, Industry, Target audience, Region, etc.). - Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for the processing of user data.
- Capability inventory: None detected; the skill generates text only and lacks the ability to execute system commands, make network requests, or perform file system operations.
- Sanitization: Absent; there are no instructions to validate or sanitize the input provided by the user before it is incorporated into the generated templates.
Audit Metadata