ln-781-build-verifier
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute shell commands for dependency restoration and project building (e.g.,
npm install,dotnet build,cargo build). These commands are derived from the local environment and project manifests. - [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection as it ingests instructions from untrusted sources to determine its actions. 1. Ingestion points: Processes project manifests (package.json, Cargo.toml, pyproject.toml, pom.xml, etc.) and internal project documentation (docs/project/*.md) to identify build commands. 2. Boundary markers: No specific delimiters or instructions are used to prevent the agent from obeying malicious instructions embedded within the manifests or documentation files. 3. Capability inventory: Employs Bash and Monitor capabilities to execute arbitrary shell commands discovered during the detection phase. 4. Sanitization: Lacks sanitization or validation of the commands extracted from project files before they are passed to the shell execution tools.
Audit Metadata