handoff
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions and templates, with no executable scripts or command-line operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from prior conversation histories and file attachments to generate handoff documents. This represents a potential injection surface that is mitigated by specific instructions within the skill.
- Ingestion points: Conversation history, artifacts, and source files (SKILL.md).
- Boundary markers: Directs the agent to treat external content as evidence only, not as new instructions.
- Capability inventory: Limited to generating text-based markdown summaries or files.
- Sanitization: Includes a dedicated Sanitize before writing section requiring the redaction of secrets like passwords and API keys using [REDACTED].
Audit Metadata