Skills
Navigate
skills/green-pt/honey-for-devs/honey-eco/Gen Agent Trust Hub

honey-eco

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the ecologits Python package. While this tool is relevant to the skill's purpose of monitoring carbon footprints, it is an unversioned third-party dependency installed at runtime.
  • [COMMAND_EXECUTION]: The skill executes local scripts scripts/eco-session.js and scripts/eco_report.py using Node.js and Python to generate usage reports from the repository's data.
  • [PROMPT_INJECTION]: The skill processes session data, creating a surface for indirect prompt injection.
  • Ingestion points: Session transcripts are ingested via the --transcript flag in scripts/eco-session.js (referenced in SKILL.md).
  • Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings for the agent when processing the transcript content.
  • Capability inventory: The skill has the capability to execute shell commands and write output based on the processed data.
  • Sanitization: There is no mention of sanitization or filtering of external transcript content before it is processed by the reporting tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 05:43 PM
Security Audit — agent-trust-hub — honey-eco