handoff-update
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes existing handoff files that may contain untrusted content, creating a surface for indirect prompt injection.
- Ingestion points: The agent is instructed to 'Read the resolved file completely' in Step 2 of
SKILL.mdto establish a baseline for merging. - Boundary markers: There are no specific delimiters or 'ignore embedded instructions' warnings provided to the agent to distinguish between data and potential instructions within the handoff file.
- Capability inventory: The skill possesses file-read and file-write capabilities across the local filesystem to update documents.
- Sanitization: No sanitization or validation of the input file content is specified before the agent parses and merges the sections.
- [SAFE]: The skill references a command template from the PackmindHub organization's public GitHub repository.
Audit Metadata