dash-audit
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill involves command execution in its workflow:
- It executes a specific local binary at
/home/bjorn/.codex/skill-support/bin/ui-audit-preflightto perform a callback map. - It directs the agent to verify paths using "repo-native commands" during remediation steps.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted repository data:
- Ingestion points: Reads
AGENTS.mdand other Dash-related source files from the target repository. - Boundary markers: No delimiters or instructions are provided to the agent to ignore embedded instructions in the ingested files.
- Capability inventory: Executes a preflight binary and performs extensive file system reads.
- Sanitization: There is no mention of sanitizing or validating the input data from the repository before it is processed by the agent.
Audit Metadata