weekly-report
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate structured reports, which presents an attack surface for indirect prompt injection.
- Ingestion points: The skill collects raw work descriptions from the user in 'Step 1: 收集素材' in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the user's input.
- Capability inventory: The skill possesses the capability to write the generated content to the local file system as documented in the '输出物存放' section of SKILL.md.
- Sanitization: No sanitization, escaping, or validation of user-provided content is defined before the content is interpolated into the final document or written to disk.
Audit Metadata