resume-handoff
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external files (handoffs, research notes, and plans) and uses this untrusted data to synthesize its analysis and generate prompts for specialist sub-agents.
- Ingestion points: The skill reads files from paths such as
thoughts/shared/handoffs/,thoughts/shared/plans/, andthoughts/shared/research/, as well as any file path provided by the user. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are utilized when processing the content of these documents; the skill is explicitly instructed to read the documents "FULLY".
- Capability inventory: The skill possesses the ability to spawn specialist sub-agents via the
Tasktool (e.g.,kraken,spark,sleuth), write task lists viaTodoWrite, and read arbitrary files using theReadtool. - Sanitization: There is no evidence of sanitization, validation, or filtering of the external content before it is interpolated into prompts for the AI or the specialist agents.
Audit Metadata