afk-unarchive-artifact

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to process and move archived artifacts, which creates a surface for indirect prompt injection if the archived content contains malicious instructions designed to influence the agent upon restoration.
  • Ingestion points: Archived artifact files located in the 'artifacts/archive/' directory.
  • Boundary markers: The instructions do not specify the use of markers, delimiters, or 'ignore instructions' warnings when handling or restoring archived content.
  • Capability inventory: The workflow involves file system operations, specifically moving files and updating documentation like 'ARCHIVE.md'.
  • Sanitization: There is no requirement for content validation, filtering, or sanitization of the restored artifact data.
  • [NO_CODE]: The skill consists exclusively of instructional markdown and does not include scripts, executables, or external dependency definitions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 11:03 PM
Security Audit — agent-trust-hub — afk-unarchive-artifact