skills/simpleeve/eo-skills/eo-archive/Gen Agent Trust Hub

eo-archive

Pass

Audited by Gen Agent Trust Hub on May 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a constrained workflow for managing local documentation, reading and modifying files based on a local project configuration file (.eo-project.json).
  • [PROMPT_INJECTION]: The skill features an indirect prompt injection surface where it reads and incorporates data from change records (change.md) into specification documents.
  • Ingestion points: The skill reads metadata and summaries from change and review records within the project documentation folder.
  • Boundary markers: There are no explicit delimiters used to isolate external content within the specification files.
  • Capability inventory: The skill's capabilities are limited to reading local files and performing text edits via standard tools. It lacks network access, shell command execution, or other high-impact capabilities.
  • Sanitization: Content is merged mechanically without specific sanitization or escaping mechanisms.
  • Assessment: Due to the lack of dangerous tools or external communication, the ingestion of untrusted data within the documentation workflow does not present a significant security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
May 24, 2026, 04:05 AM
Security Audit — agent-trust-hub — eo-archive