vault-archive-audit

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists exclusively of markdown instructions and does not include any scripts, binaries, or executable code.
  • [SAFE]: Operations are restricted to local file system moves (archival) with no evidence of network exfiltration, credential access, or privilege escalation.
  • [SAFE]: The instructions include safety boundaries that prohibit content deletion and limit the agent's scope to specific curated directories.
  • [PROMPT_INJECTION]: The skill's workflow involves scanning vault files, which creates a surface for indirect prompt injection. The risk is minimal as the skill lacks high-risk capabilities like network access or code execution.
  • Ingestion points: Scanning files in projects/ and notes/ (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: File move (archive) and file write (append to log.md).
  • Sanitization: None present.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 12:34 AM
Security Audit — agent-trust-hub — vault-archive-audit