social-media-api-integration

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a distribution pipeline that takes content from the 'Post' object and sends it to external social media APIs, representing an indirect prompt injection surface.
  • Ingestion points: 'Post' dataclass and 'distribute' method in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Network POST requests to social media platforms in SKILL.md.
  • Sanitization: Absent (only length truncation is performed).
  • [DATA_EXFILTRATION]: The skill performs network operations to well-known social media services (LinkedIn, Mastodon, Bluesky, Dev.to). It follows security best practices by advising against hardcoding credentials in the anti-patterns section and recommending environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 03:25 AM