skill-troubleshooting

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes PowerShell commands to search, read, and write to a local troubleshooting database. This allows the agent to interact with the file system to manage issue logs.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local YAML and Markdown files to determine troubleshooting steps. This introduces a vulnerability where malicious instructions embedded in those files could influence the agent's actions or lead to unauthorized file access if the source data is compromised.\n
  • Ingestion points: .agents/troubleshooting/known-issues.yaml and resolution files located in ..claude/troubleshooting/.\n
  • Boundary markers: The skill does not use specific delimiters or warnings to ignore instructions within the ingested troubleshooting data.\n
  • Capability inventory: The skill possesses file system read and write capabilities via PowerShell (Get-Content, ConvertFrom-Yaml, etc.).\n
  • Sanitization: There is no evidence of sanitization or validation of the content retrieved from the troubleshooting files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 01:17 AM