feature-spec
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingest data from external feature specification files and documentation when performing updates or referencing research via the @file syntax. While this creates a standard surface for indirect prompt injection, the risk is mitigated by the skill's limited capabilities.\n
- Ingestion points: The skill searches for and reads content from paths such as specs/, features/, requirements/, and docs/specs/, as well as user-referenced files via @file.\n
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the documents being processed.\n
- Capability inventory: The skill is restricted to reading and writing local text files (feature specs). It does not have access to network tools, shell execution, or sensitive system credentials.\n
- Sanitization: There is no explicit sanitization or filtering of the content read from existing documents before it is processed by the agent.
Audit Metadata