docstore-status

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill instructs the agent to use the Bash tool to run stat on file paths obtained from .docstore/sources.yaml. If the YAML file contains malicious file paths with shell metacharacters (e.g., ;, &, or backticks), it could lead to command injection.- [PROMPT_INJECTION] (LOW): Indirect prompt injection surface via untrusted local metadata. \n
  • Ingestion points: .docstore/sources.yaml and meta.yaml. \n
  • Boundary markers: Absent. The skill does not define delimiters or provide instructions to ignore content within the processed files. \n
  • Capability inventory: Uses Bash, Read, Glob, and Grep, which allow for significant system interaction if an injection is successful. \n
  • Sanitization: Absent. There is no requirement for validating the integrity or content of the YAML files or the file paths they contain before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 03:28 PM