ppppp
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted user input ("原始需求") and interpolate it directly into a library of predefined prompt templates found in
references/templates.md. - Ingestion points: The primary ingestion point is the user-provided input passed as an argument to the skill in
SKILL.md(Section VI). - Boundary markers: The skill lacks explicit boundary markers or instructions to the model to ignore or escape control characters/instructions that might be embedded within the user's input.
- Capability inventory: The skill itself has low capability risk; it is configured with
disable-model-invocation: trueand primarily outputs text. It does not perform file system writes, network requests, or command executions. - Sanitization: There is no evidence of input validation, escaping, or sanitization before the user text is placed into the
【】placeholders in the templates.
Audit Metadata