skills/clawic/skills/Indonesia/Gen Agent Trust Hub

Indonesia

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to maintain a persistent local state file to track user trip details, which creates a vulnerability surface where malicious input could influence future agent behavior.
  • Ingestion points: User trip preferences and constraints are ingested through dialogue and stored in the ~/Clawic/data/indonesia/memory.md file, as specified in SKILL.md and setup.md.
  • Boundary markers: The memory structure follows a markdown template (memory-template.md), but the instructions do not include specific delimiters or warnings to the agent to ignore potentially malicious instructions embedded within the stored data.
  • Capability inventory: The skill is permitted to read and write within its own data directory (~/Clawic/data/indonesia/). It does not have access to general shell execution, network operations, or external file paths.
  • Sanitization: There are no explicit mechanisms described for sanitizing or validating user input before it is committed to the local memory file.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 03:46 PM