skill-testing

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute specific local scripts for error detection, namely scripts/error-detection.ps1 on Windows and scripts/error-detection.sh on macOS/Linux.
  • [DATA_EXPOSURE]: The skill instructs the agent to read a specific file from the user's Documents folder (Documents/APC_CRASH_REPORT.txt) to perform crash analysis.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection by reading and acting upon data from external sources like crash reports and configuration files.
  • Ingestion points: Documents/APC_CRASH_REPORT.txt and .agents/troubleshooting/known-issues.yaml.
  • Boundary markers: Absent; the instructions do not specify any delimiters or warnings to ignore embedded instructions in the ingested files.
  • Capability inventory: The skill has the capability to execute local scripts and potentially perform actions based on the parsed output of the ingested files.
  • Sanitization: Absent; there is no mention of sanitizing or validating the content of the crash reports or YAML configuration before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 01:17 AM