Skills
skills/pedrohcgs/claude-code-my-workflow/context-status/Gen Agent Trust Hub

context-status

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes cat and ls commands to list files and read session data from the local filesystem.
  • [DATA_EXFILTRATION]: Reads from the sensitive path ~/.claude/sessions/ to extract context monitor data. While used for reporting session health, accessing the user's application configuration directory is an exposure risk.
  • [PROMPT_INJECTION]: Vulnerable to indirect prompt injection if an attacker can manipulate the content of context-monitor-cache.json or the names of files in quality_reports/ which are then displayed to the agent.
  • Ingestion points: ~/.claude/sessions/*/context-monitor-cache.json and file listings in quality_reports/.
  • Boundary markers: None present.
  • Capability inventory: Filesystem read access via cat and ls.
  • Sanitization: No escaping or validation is applied to the retrieved data before it is presented.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 09:07 AM