asking-clarifying-questions
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of data from several untrusted or externally-controlled sources, including user input and research results from subagents. This architecture presents an attack surface for indirect prompt injection where malicious instructions embedded in the analyzed content could attempt to influence the agent's behavior.
- Ingestion points: The skill ingests raw user requirements, codebase content retrieved via
codebase-investigator, internet search data viacombined-researcher, and remote product management datastore information viahaiku-general-purposesubagents. - Boundary markers: Absent. The instructions do not define specific delimiters or warnings to isolate external data from the agent's core instructions.
- Capability inventory: The skill possesses the capability to query the codebase, perform web searches, access remote datastores, and interact directly with the user through tools like
AskUserQuestion. - Sanitization: Absent. There is no mention of filtering, escaping, or validating content retrieved from external sources before it is processed by the agent.
Audit Metadata