building-api-authentication
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's implementation workflow involves reading external API specifications, which presents a potential surface for indirect prompt injection if the ingested files contain malicious instructions.
- Ingestion points: The skill reads API specifications from the
${CLAUDE_SKILL_DIR}/api-specs/directory using theReadtool as outlined inreferences/implementation.md. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the specifications are provided in the implementation steps.
- Capability inventory: The skill utilizes the
Write,Edit, and a restrictedBash(api:auth-*)tool to generate and modify code based on the ingested specifications. - Sanitization: There are no documented steps for validating or sanitizing the input data from the API specifications before it is used to drive code generation tasks.
Audit Metadata