skills/pashza/claude-seo/seo-flow/Gen Agent Trust Hub

seo-flow

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a /seo flow sync command that executes a local script named sync_flow.py via the claude-seo runtime to manage file updates.
  • [EXTERNAL_DOWNLOADS]: The synchronization logic fetches prompt updates from the official public GitHub repository for the FLOW framework (github.com/AgriciDaniel/flow). This is a user-initiated administrative action for the skill.
  • [PROMPT_INJECTION]: The skill processes user-supplied URLs and topics through a variety of SEO templates, which presents a surface for indirect prompt injection. This risk is mitigated by the inclusion of a checksum file (references/flow-prompts.lock) that uses SHA-256 hashes to ensure the integrity of the prompt library files.
  • [SAFE]: The reference materials and bibliography consistently cite well-known and authoritative services such as Google Search Central, Ahrefs, Backlinko, and the SEC for SEO claims and behavioral data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 07:29 PM