cursor-run-learning-retrospective
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to review 'completed work,' which serves as an entry point for untrusted data that could contain malicious instructions.
- Ingestion points: Workflow step 1 in
SKILL.md('Review completed work against target outcomes'). - Boundary markers: No delimiters or instructions to ignore embedded commands are present in the workflow.
- Capability inventory: The skill is limited to conversational analysis and use of the 'Ask user' tool. No file system access, network operations, or shell command execution tools are defined or referenced.
- Sanitization: There is no evidence of sanitization or validation logic for the processed work data.
Audit Metadata