sharpen-auto
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content (rough or confusing user prompts) to rewrite them. This creates an attack surface where instructions embedded within the user's input could attempt to influence the agent's behavior during the refinement process.
- Ingestion points: The skill ingests untrusted text provided by the user in the form of rough prompts (SKILL.md).
- Capability inventory: The skill uses the
AskUserQuestiontool for interaction but does not demonstrate file system, network, or shell execution capabilities (SKILL.md). - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the input text.
- Sanitization: No specific sanitization or filtering logic is defined, although the process requires a human review and confirmation step (
confirm via AskUserQuestion) before providing the final output.
Audit Metadata