task
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface. \n
- Ingestion points: The skill ingests untrusted data from
plan.md,backlog.md, and other repository files usingRead,Grep, andGlobtools as defined inSKILL.mdand the agent files. \n - Boundary markers: There are no explicit delimiters or boundary markers used to separate external file content from the agent's internal instructions, allowing potential instructions within a plan to be interpreted as commands. \n
- Capability inventory: The skill possesses
EditandWritecapabilities (task-tracker.md,wrap-coordinator.md), enabling it to modify the file system based on its processing of the input documents. \n - Sanitization: No evidence of sanitization, filtering, or validation is present for the content read from files before it is processed by the agent.
Audit Metadata