scan
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted user data (modified or generated code files).
- Ingestion points: Instructions in
SKILL.mddirect the agent to read the full content of all files that were generated, added, or modified. - Boundary markers: The instructions do not define clear delimiters or escaping mechanisms when processing the content of these files.
- Capability inventory: The skill can invoke the
aikido-mcp:aikido_full_scantool and is instructed to apply remediation fixes to files based on the scan output. - Sanitization: There is no explicit sanitization step described in the skill; it relies on the tool and the agent's internal safety layers to handle potentially malicious content inside scanned files.
Audit Metadata