intent-report
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process technical 'Intent' files (project-level and module-level) to generate human-readable reports. This functionality creates an attack surface where instructions embedded within the technical source data could influence the agent's behavior during the conversion process.
- Ingestion points: Technical 'Intent' files located in the project directory (e.g.,
src/core/). - Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions within the source files.
- Capability inventory: The skill involves reading local files, parsing metadata, and writing output in various formats (Markdown, HTML, PDF) to the local file system.
- Sanitization: No explicit sanitization or filtering of the input file content is mentioned, though it applies content transformation rules for readability.
Audit Metadata