managing-up
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- PROMPT_INJECTION (SAFE): No malicious instructions or bypass attempts were detected. The skill includes clear 'When NOT to use' sections to guide the AI away from sensitive HR or legal scenarios.
- DATA_EXFILTRATION (SAFE): The skill explicitly instructs users and the AI not to request or provide secrets, passwords, tokens, or PII. It suggests using anonymized summaries for all communication artifacts.
- REMOTE_CODE_EXECUTION (SAFE): There are no scripts, binaries, or external dependencies included in this skill. It operates entirely through text-based prompts and templates.
- COMMAND_EXECUTION (SAFE): No shell commands, subprocess calls, or system-level operations are present.
- INDIRECT_PROMPT_INJECTION (SAFE): While the skill processes user-provided context about their workplace, it lacks the 'exploitable capabilities' (such as network access or code execution) necessary to facilitate a high-risk indirect injection attack.
Audit Metadata