sociuu-recap
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's functionality involves reading conversation and task history, which could contain untrusted data. This represents a potential surface for indirect prompt injection, but it is considered safe here as the skill does not use any tools or commands that could be exploited.
- Ingestion points: The skill refers to 'available history' and 'relevant completed work' in SKILL.md.
- Boundary markers: No explicit delimiters are instructed for the history content.
- Capability inventory: The skill is restricted to text generation and does not define any tool use or code execution.
- Sanitization: No sanitization instructions are provided for the input history content.
- [SAFE]: No security threats, obfuscation, or malicious instructions were detected within the skill content.
Audit Metadata