product-sprint-prioritizer
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected in the skill instructions or scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as an interface for processing user-defined tasks, which represents a potential ingestion point for untrusted instructions.
- Ingestion points: User input is accepted via the
--taskargument or standard input inscripts/run.sh. - Boundary markers: The
SKILL.mdfile does not define explicit delimiters or instructions to ignore embedded commands within user data. - Capability inventory: No dangerous operations (file writing, network requests, or arbitrary command execution) are defined within the skill's scripts.
- Sanitization: There is no evidence of input validation or escaping for the user-supplied task data.
Audit Metadata