marketing-agency
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill manages a surface for indirect prompt injection by ingesting untrusted data from external URLs and local brand documentation.
- Ingestion points: Defined in
references/shared-patterns.md(Context C: Live Website URL Audit) andSKILL.md(brand context files). - Boundary markers: Absent; no delimiters or instructions are provided to the agent to ignore potentially malicious content within retrieved data.
- Capability inventory: The skill can perform file system writes (
SKILL.md), invoke specialist marketing skills (references/team-spawning.md), and execute shell commands for dependency installation. - Sanitization: Absent; the skill uses processed data directly to formulate strategic recommendations without explicit validation.
- [EXTERNAL_DOWNLOADS]: The skill references the installation of the
agent-browsertool from Vercel Labs' official GitHub repository to facilitate market research and audits.
Audit Metadata