seo-authority
Warn
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructs the agent to execute scripts from a path () that is dynamically resolved by reading a local configuration file (.seo-suite-runtime.json) or an environment variable ($CLAUDE_PLUGIN_ROOT). This represents dynamic loading from computed paths.\n- [COMMAND_EXECUTION]: The skill requires running multiple Python scripts, including validate_seo_findings.py, manage_markdown_site.py, and manage_markdown_work.py, with arguments that include file paths and bundle identifiers.\n- [INDIRECT_PROMPT_INJECTION]: The skill audits external, untrusted content such as anchor text, brand mentions, and referring evidence from arbitrary web sources. This content is ingested into the agent's context.\n
- Ingestion points: Untrusted data enters via backlink profiles and source landscape evidence, specifically anchor text and mention context as described in SKILL.md and references/authority-evidence-protocol.md.\n
- Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions embedded within the audited text.\n
- Capability inventory: The agent can execute Python scripts via the shell and perform file system writes to generate audit reports and update indices.\n
- Sanitization: No sanitization or escaping of the external data is specified before it is processed or included in findings.
Audit Metadata