lov-output-wechat-moment
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to format it for social media, presenting a surface for indirect prompt injection.
- Ingestion points: Processes user-specified content as defined in the SKILL.md workflow.
- Boundary markers: The instructions do not define specific delimiters or instructions to treat input as data rather than instructions.
- Capability inventory: Includes file writing capabilities (SKILL.md) and local profile modification via the scripts/profile_store.py utility.
- Sanitization: While the workflow instructs the agent to output plain text and avoid markdown formatting, it does not explicitly sanitize the input data to prevent instruction injection.
Audit Metadata