prompt-set-qa
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any scripts, executables, or external dependencies, which significantly reduces the technical attack surface.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, creating a potential surface for indirect prompt injection.
- Ingestion points: Data enters the agent context via
prompt_universe.json,prompt_architecture.json, evidence excerpts, and source metadata as defined in the Inputs section. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the prompts being reviewed.
- Capability inventory: The skill is limited to generating Markdown reports and writing analysis results to a local file (
prompt_qa.json). It does not have access to network tools or shell commands. - Sanitization: There is no mention of sanitizing or escaping the content of the candidates before processing.
Audit Metadata