storage-audit

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to navigate to a specific directory (~/.hermes/profiles/matias) and execute a local shell script (./scripts/storage-hygiene.sh). This script performs disk cleanup operations such as pruning caches and deleting idle worktrees.\n- [INDIRECT_PROMPT_INJECTION]: The agent is required to read and summarize output from system logs and script results to generate a report. \n
  • Ingestion points: storage-hygiene.log, history.log, and the stdout of the storage-hygiene.sh script. \n
  • Boundary markers: None explicitly defined in the instructions to separate log content from agent instructions. \n
  • Capability inventory: The agent can execute shell scripts and access local files as defined in the skill scope. \n
  • Sanitization: The skill provides a rigid reporting template which limits the agent's output flexibility and helps focus processing on specific data points, mitigating potential injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 09:34 AM
Security Audit — agent-trust-hub — storage-audit