cursor-common-errors
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection where malicious instructions could be embedded in user-provided error reports.
- Ingestion points: User input describing errors via triggers in SKILL.md.
- Boundary markers: Absent; no delimiters are used to wrap user input.
- Capability inventory: Unrestricted Bash(cmd:*), Read, Write, and Edit tools.
- Sanitization: Absent; no input validation or filtering is specified.
- [COMMAND_EXECUTION]: The skill uses allowed-tools: Bash(cmd:*) in SKILL.md, which allows the agent to execute any system command for troubleshooting, increasing the potential impact of an injection attack.
Audit Metadata