linkedin-content-planner
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user data (Theme, Audience description, Voice samples) which creates a surface for indirect prompt injection. The risk is significantly mitigated by the lack of execution tools.
- Ingestion points: User-provided text inputs defined in the 'Input' section of
SKILL.md(Theme, Audience description, Voice samples). - Boundary markers: The skill lacks explicit delimiters or system instructions to isolate user-provided data from the core logic.
- Capability inventory: None. The skill does not list any
allowed-toolsin its frontmatter and contains no executable Python or JavaScript files. - Sanitization: No input validation or filtering of user-supplied strings is described or implemented.
Audit Metadata