social-selling-content-generator-skill
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it interpolates untrusted user data (target audience, solutions, and goals) into its workflow while having the capability to write to the local file system. Ingestion points: User-provided inputs for audience, solution, and goals entering the agent context via the quick start triggers in SKILL.md. Boundary markers: Absent; user inputs are not enclosed in delimiters or accompanied by instructions to ignore embedded commands. Capability inventory: File-write capability used to emit an outcome sidecar to ~/.claude/skill-analytics/ (SKILL.md). Sanitization: Absent; the skill does not define methods for escaping or validating user-provided strings before processing.
Audit Metadata