skills/opencue/colony/co-archive/Gen Agent Trust Hub

co-archive

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious code, obfuscated content, or suspicious network operations were identified. The skill's behavior is consistent with its stated purpose of managing change archives within a project directory.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes content from external CHANGE.md files during the verification and archiving process.
  • Ingestion points: The file openspec/changes/<slug>/CHANGE.md is read in step 1 of the procedure.
  • Boundary markers: There are no specific delimiters or instructions to ignore embedded commands within the processed file.
  • Capability inventory: The skill triggers the spec_archive tool, which has the capability to write to and move files within the repo_root.
  • Sanitization: No sanitization or validation of the text content within CHANGE.md is specified before it is processed by the agent or the archive tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 11:36 PM
Security Audit — agent-trust-hub — co-archive