operational-readiness
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data by scanning local codebase files (e.g., configuration files, source code, and CI/CD pipelines) to generate its readiness report. This creates a potential surface where malicious instructions embedded in the audited code could attempt to influence the agent's evaluation.
- Ingestion points: Reads project-specific files such as
package.json,Cargo.toml,*.tf, and GitHub Action workflows. - Boundary markers: The instructions do not explicitly require the agent to use delimiters or ignore embedded instructions when reading these files.
- Capability inventory: The skill uses
GlobandGrepfor targeted analysis andAskUserQuestionfor interactive verification. - Sanitization: There are no specific instructions for escaping or filtering the content gathered from the codebase before the agent processes it.
Audit Metadata