ai-code-blindspots
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted code data through an LLM sub-agent to identify coding errors, creating an attack surface for indirect prompt injection.
- Ingestion points: Code content is ingested from the file system via
git diffor caller-provided file lists. - Boundary markers: There are no explicit delimiters or instructions provided to the sub-agent to ignore potential instructions embedded within the analyzed code.
- Capability inventory: The skill uses
Read,Bash,Glob, andGreptools. - Sanitization: The skill does not describe any sanitization or filtering of the input code before it is passed to the analysis layer.
- [COMMAND_EXECUTION]: The skill executes shell commands such as
git diff,grep, andgit hash-objectto scope analysis and generate uniquely identified report artifacts. These are functional requirements for its code auditing purpose.
Audit Metadata