configure-auth
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to read
AGENTS.mdfrom the workspace root to determine interactivity mode and project scope before performing any authentication configuration. This creates a surface where malicious instructions embedded in project documentation could influence the agent's behavior. \n - Ingestion points:
AGENTS.md(referenced in Step 1). \n - Boundary markers: None specified for the content read from
AGENTS.md. \n - Capability inventory: The skill facilitates modification of C# and Razor files and configuration of security services. \n
- Sanitization: No sanitization or validation of the input from
AGENTS.mdis described.
Audit Metadata