ds-sharpen
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill requires the agent to generate and run probe scripts or tests to validate weaknesses in a provided plan. This involves runtime code generation and execution as part of the stress-test phase.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied goals and plans as its primary input, which could potentially contain malicious instructions.\n
- Ingestion points: User goals and plans are ingested in SKILL.md (Step 1 and Step 4).\n
- Boundary markers: The skill does not define explicit delimiters or instructions to disregard embedded commands in the input data.\n
- Capability inventory: The skill can execute shell commands, probe scripts, and spawn subagents based on the provided plan.\n
- Sanitization: No sanitization or validation of the input plan is described before it is used to drive command execution and script generation.
Audit Metadata