inngest-brownfield-audit
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
rg(ripgrep) utility to perform targeted searches within the local repository. These commands are used for project discovery and architectural mapping, focusing on frameworks, dependencies, and code patterns related to background tasks. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted data (source code and configuration files) from the repository undergoing the audit. An attacker could place malicious instructions in code comments or string literals within the audited files to influence the agent's integration plan or suggested modifications.
- Ingestion points: Source code,
package.json, router structures, and deployment configurations are read from the repository usingrgand file system access. - Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to disregard natural language instructions embedded within the codebase being audited.
- Capability inventory: The agent possesses the capability to execute shell commands (discovery via
rg) and modify the repository's files to implement integration plans. - Sanitization: There is no evidence of sanitization or validation performed on the codebase content before it is processed by the agent to generate summaries and integration code.
Audit Metadata