session-navigation

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard shell commands (ls, grep, jq, rg, wc, cat, head) to search and read local session files.
  • Evidence: Found in multiple usage examples in SKILL.md targeting the ~/.factory/sessions/ directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from past session logs, which could theoretically contain malicious instructions embedded in previous conversation history.
  • Ingestion points: The agent reads content from ~/.factory/sessions/*.jsonl files using head, rg, and cat.
  • Boundary markers: No explicit boundary markers or 'ignore' instructions are provided when reading session data.
  • Capability inventory: The skill has read-only access to specific files and utilizes common Unix utilities for processing.
  • Sanitization: No sanitization of the session content is performed before presenting it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 04:37 PM
Security Audit — agent-trust-hub — session-navigation