codeprobe-error-handling
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing untrusted external data with shell-level capabilities.
- Ingestion points: The skill uses Read, Grep, and Glob tools to ingest source code from the project environment (SKILL.md).
- Boundary markers: No delimiters or explicit instructions are provided to separate the audited code content from the agent's instructions, potentially allowing the agent to follow commands embedded in the source code.
- Capability inventory: The skill is configured with the Bash tool, providing a powerful environment for command execution.
- Sanitization: The skill does not implement any validation, escaping, or filtering for the content ingested from the scanned files.
Audit Metadata