ralph-copywriter
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing external, untrusted data.
- Ingestion points: The skill actively reads and analyzes user-provided content, social media profiles (Twitter/LinkedIn), and competitor websites during its discovery and research phases.
- Boundary markers: The instructions do not define specific delimiters or safety warnings to prevent the agent from following instructions that may be embedded in analyzed external content.
- Capability inventory: The skill is restricted to text analysis and content generation; it lacks access to shell commands, network exfiltration tools, or filesystem write operations.
- Sanitization: There is no mention of sanitizing or validating the retrieved external data before it is processed by the agent.
- [NO_CODE]: This skill consists entirely of markdown documentation and does not include any scripts, binaries, or configuration files that execute code.
Audit Metadata