Affirmations
Pass
Audited by Gen Agent Trust Hub on Jun 6, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns, suspicious network activity, or unauthorized file access were detected.
- [NO_CODE]: The skill does not include any scripts or executable code, relying solely on natural language instructions for the agent to interact with local files.
- [DATA_EXFILTRATION]: No network operations or data transmission patterns were found. The skill only interacts with local files in a dedicated workspace (~/affirmations/).
- [PROMPT_INJECTION]: The skill reads and processes user-provided affirmations from local files which represents an indirect injection surface. (1) Ingestion points: Markdown files in ~/affirmations/ (SKILL.md). (2) Boundary markers: None. (3) Capability inventory: None; no command execution or network tools are used. (4) Sanitization: None. Risk assessment: The risk is negligible as the skill lacks high-privilege capabilities or network access to exploit.
Audit Metadata