github-actions-starter
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to manage and validate GitHub Actions configurations, which involves reading and processing potentially untrusted workflow files and CI/CD patterns. The combination of data ingestion and powerful execution capabilities (Bash, Write, Edit) creates a surface where malicious instructions embedded in project files could influence the agent's behavior.
- Ingestion points: The skill processes user-provided requests and local project files related to GitHub Actions, CI/CD patterns, and DevOps fundamentals (SKILL.md).
- Boundary markers: The skill lacks explicit instructions or delimiters to isolate processed data or to warn the agent to ignore embedded instructions within workflow configurations.
- Capability inventory: The skill is granted access to Bash (cmd:*), Write, Edit, Read, and Grep tools, which allow for significant system and file modifications.
- Sanitization: There are no explicit sanitization, validation, or filtering requirements mentioned for the external content processed by the skill.
Audit Metadata