social-post-writer

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data such as topics, personal stories, and constraints to generate social media posts, which constitutes an ingestion surface for untrusted content.
  • Ingestion points: SKILL.md
  • In Step 1, the agent prompts for "Topic or idea", "Personal experience or proof points", and "Constraints".
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or specific warnings to ignore embedded instructions within user-provided strings.
  • Capability inventory: The skill is strictly limited to text generation and formatting. No command execution (subprocess calls), file system writes, or network operations are present in the instructions.
  • Sanitization: Absent; there is no mechanism provided to sanitize or filter potential injection attempts within the user-provided topic inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 08:05 AM
Security Audit — agent-trust-hub — social-post-writer