troubleshooting-docs
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input from conversation history to generate documentation and search existing files.
- Ingestion points: User-confirmed symptoms, exact error messages, and solution steps extracted in Step 2.
- Boundary markers: No explicit delimiters or instructions are used to separate user data from the agent's instructions during documentation creation or searching.
- Capability inventory: The skill uses
Bash(grep, mkdir, echo, cat) andWritetools to interact with the file system. - Sanitization: While Step 4 mentions a sanitized symptom for filenames, no specific sanitization or escaping is mandated for error strings used in shell commands like
grep. - [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (
grep,mkdir,echo,cat) to manage the documentation library. This presents a risk of command injection if the agent interpolates unsanitized user input containing shell metacharacters (e.g., backticks, semicolons) into the command strings.
Audit Metadata