codebase-audit
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection from the codebases it audits. Malicious content within source code, comments, or documentation could be used to override the auditor's instructions or suppress specific findings.
- Ingestion points: The skill reads all files within the target directory ({TARGET_DIR}) during analysis.
- Boundary markers: Absent. The prompt templates in
references/agent-prompts.mddo not utilize delimiters (like triple backticks or XML tags) or specific instructions to treat the ingested code as data only. - Capability inventory: The skill utilizes multiple specialized agents (reviewer, security-reviewer, architect) with broad file-reading and analysis capabilities to generate a comprehensive report.
- Sanitization: There is no evidence of sanitization or filtering applied to the code snippets before they are processed by the agents.
Audit Metadata