obsidian-cli-uri-fallback

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No prompt injection or behavior override patterns detected. The instructions are focused on standard error handling and file persistence logic.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive data exposure, hardcoded credentials, or network exfiltration patterns found. The skill interacts with the local file system to save notes to an Obsidian vault as intended.
  • [OBFUSCATION]: No obfuscated content, encoded strings, zero-width characters, or hidden URLs were identified.
  • [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: No remote code execution or external script downloads detected. The skill uses a local obsidian-cli tool and standard bash utilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes output from the obsidian-cli command to detect failure signatures.
  • Ingestion points: obsidian-cli stdout/stderr (SKILL.md)
  • Boundary markers: Absent
  • Capability inventory: Bash (subprocess), Write (file system write)
  • Sanitization: Absent
  • Analysis: Although the skill processes external command output, it does so to trigger a local file-writing fallback. The actions are limited to the intended automation scope without high-risk capability chaining.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 07:06 AM
Security Audit — agent-trust-hub — obsidian-cli-uri-fallback