handoff
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill's behavior is consistent with its stated purpose of creating handoff documentation.- [DATA_EXPOSURE]: While the skill handles conversation data, it mitigates exposure risks by explicitly instructing the agent to redact sensitive information (API keys, passwords, and PII) before persisting the summary to the filesystem.- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it ingests conversation history (untrusted data source). However, it includes sanitization instructions (redaction) and its capabilities are restricted to writing files within the 'docs/handoff/' directory in the workspace. No boundary markers are used, but the task is inherently localized to documentation generation.
Audit Metadata