project-context-ingestion
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process various files from a repository, including build scripts (build.gradle.kts), configuration files (application.yml), and CI/CD manifests. This creates a surface for indirect prompt injection if the repository contains malicious instructions designed to influence the agent's behavior.
- Ingestion points: Reading of settings.gradle.kts, build.gradle.kts, gradle.properties, application.yml, and other repository files.
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: The skill focuses on information gathering and summarization; however, the agent's broader environment likely includes file-writing and command-execution capabilities used in subsequent steps.
- Sanitization: No specific sanitization of file content is mentioned.
Audit Metadata