sprint-planning-helper
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The analyzed file consists only of metadata and instructional text; no obfuscation, hardcoded credentials, or malicious commands were found.
- [Indirect Prompt Injection] (LOW): The skill is designed to process untrusted data from user requests via auto-trigger phrases and has access to powerful capabilities. Evidence Chain: 1. Ingestion points: User-provided phrases such as 'sprint planning helper'. 2. Boundary markers: None specified in the instructions to separate user input from agent logic. 3. Capability inventory: The skill allows use of 'Read', 'Write', 'Edit', and 'Bash' tools. 4. Sanitization: No evidence of input validation or command escaping provided in the definition.
Audit Metadata