external-authority-placement-scout

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from external sources to identify SEO opportunities, which presents a surface for indirect prompt injection.
  • Ingestion points: External content gathered from "user-provided platforms" and "approved public research" as defined in the Workflow section of SKILL.md and references/scouting-workflow.md.
  • Boundary markers: Absent. The instructions do not specify using delimiters or explicit warnings to ignore embedded commands when processing external text.
  • Capability inventory: The agent is restricted to local file reading, draft generation, and local subprocess execution for validation scripts (lint_production_skill.py, lint_skill_cluster.py). Automated external actions like posting, account edits, or outreach are explicitly forbidden.
  • Sanitization: Absent. The workflow does not include steps to sanitize or filter potential malicious instructions from the analyzed external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 07:30 AM
Security Audit — agent-trust-hub — external-authority-placement-scout