interview
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core function involves reading and processing external files provided by the user, which presents a surface for potential instructions embedded within those files to influence the agent.\n
- Ingestion points: Reads the file specified in the
<plan-file>argument as defined in the activation protocol.\n - Boundary markers: The instructions do not include specific delimiters or directives to ignore instructions that might be contained within the input plan file.\n
- Capability inventory: The skill is capable of reading local files, interacting with the user via
AskUserQuestion, and writing or appending summaries to files upon completion.\n - Sanitization: The skill does not implement specific sanitization or filtering logic for the content read from the input file.
Audit Metadata