context-pack
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the conversation history to generate a handoff document, which acts as a persistence vector for instructions across agent sessions.\n
- Ingestion points: Conversation history and user-supplied arguments (SKILL.md).\n
- Boundary markers: No explicit delimiters or 'ignore' instructions are used to wrap the summarized content in the output template.\n
- Capability inventory: File system write access to save the handoff document (SKILL.md).\n
- Sanitization: While the skill requires redacting secrets (API keys, etc.), it does not include measures to escape or validate the content against malicious prompt instructions.
Audit Metadata