Skills
skills/johnefemer/skillfish/self-improving-agent-status/Gen Agent Trust Hub

self-improving-agent-status

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell commands such as wc, ls, and grep to calculate file lengths and list directory contents for health reporting.
  • [DATA_EXPOSURE]: The skill accesses project-specific memory files and configuration in the ~/.claude directory to provide metrics on memory usage, topic files, and stale references. These operations are limited to metadata analysis (line counts and file existence checks) and are consistent with the stated purpose of a health dashboard.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:18 PM
Security Audit — agent-trust-hub — self-improving-agent-status