linkedin-post-formatter

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill behaves as a pure text transformation utility. All formatting logic is contained within the skill and its local reference file, references/unicode-charmap.md. No malicious patterns such as credential exfiltration, persistence, or privilege escalation were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user content (text, HTML, or ideas) to generate formatted social media posts, creating a potential ingestion surface for indirect instructions. However, the risk is negligible as the skill lacks any dangerous capabilities.
  • Ingestion points: The skill reads 'source content (text, HTML, image, or idea)' as described in the Process section of SKILL.md.
  • Boundary markers: There are no specific delimiters or 'ignore' instructions used when processing user-provided content.
  • Capability inventory: The skill does not use any tools for network operations, file writing, or system command execution.
  • Sanitization: No input validation or escaping is applied to the source content.
  • Risk Assessment: The lack of actionable capabilities prevents an attacker from using injected instructions to perform harmful actions beyond influencing the generated text output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:33 PM
Security Audit — agent-trust-hub — linkedin-post-formatter