prod-readiness-review
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze untrusted data from repository artifacts such as build scripts, runbooks, and infrastructure code to verify production readiness.
- Ingestion points: Workflow steps in
SKILL.mddirect the agent to examine release artifacts, CI scripts, and environment configurations. - Boundary markers: There are no explicit delimiters or instructions to treat external repository data as untrusted or to ignore potentially malicious instructions embedded within those files.
- Capability inventory: While the skill body focuses on analysis, the agent's general capabilities (such as file system access or shell execution) are not explicitly restricted in the YAML frontmatter's
allowed-toolsfield. - Sanitization: The skill does not provide mechanisms for validating or sanitizing the content ingested from the repository before processing it.
Audit Metadata