knowledge-locator

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to execute a local Python script scripts/palace_manager.py to perform search, listing, and indexing operations. This behavior is consistent with the skill's stated purpose of managing and navigating stored knowledge.
  • [PROMPT_INJECTION]: The skill acts as a retrieval interface for external data sources ('memory palaces'). While this creates an attack surface for indirect prompt injection, no active malicious instructions were found in the static analysis.
  • Ingestion points: The agent ingests data returned by scripts/palace_manager.py (SKILL.md).
  • Boundary markers: There are no explicit boundary markers or instructions provided to the model to ignore potential instructions embedded in the retrieved data.
  • Capability inventory: The skill calls scripts/palace_manager.py via shell commands.
  • Sanitization: There is no evidence of sanitization or filtering of the retrieved data before it is presented to the model context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 06:22 AM
Security Audit — agent-trust-hub — knowledge-locator