launch-readiness-auditor
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external codebase content using discovery tools, which creates an attack surface for indirect prompt injection where malicious instructions embedded in project files could attempt to influence the agent's behavior.
- Ingestion points: Reads project files (README.md, architecture docs, source code) via Read, Glob, and Grep tools.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for the audited content.
- Capability inventory: The agent has access to powerful tools including Bash (command execution) and WebFetch (network access).
- Sanitization: No sanitization or validation of the ingested codebase data is performed prior to processing.
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform functional tasks such as running test suites and verifying build statuses. These operations are restricted to the intended purpose of auditing software for launch readiness.
Audit Metadata