deploy-app
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository data (such as documentation, lockfiles, and configuration files) to determine deployment strategies. This creates a surface where malicious instructions embedded in a repository's files could attempt to influence the agent's behavior.
- Ingestion points: The skill explicitly reads repository-aware evidence including existing deployment documentation, lockfiles, and framework configurations.
- Boundary markers: While the skill includes high-level "Safety gates" that require user approval for production mutations, it does not implement explicit delimiters or instruction-ignore blocks when interpolating repository content into its prompts.
- Capability inventory: The skill is capable of invoking sub-skills that generate files, configure CI/CD pipelines, and validate deployments through shell commands.
- Sanitization: No explicit sanitization or validation of the data read from the repository is described before it is used to plan or execute deployment workflows.
Audit Metadata