blog-repurpose

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted blog post content which is then used to generate social media outputs.
  • Ingestion points: The skill uses the Read tool in Step 1 to ingest the text of a blog post from the local file system.
  • Boundary markers: There are no explicit delimiters or system instructions provided to the agent to treat the blog content as non-executable data or to ignore embedded instructions.
  • Capability inventory: The skill is permitted to use Read, Write, Grep, and Glob tools. It lacks the ability to make network requests or execute system commands.
  • Sanitization: The skill does not perform any sanitization, filtering, or validation of the blog post content before processing it.
  • [SAFE]: No evidence was found of data exfiltration, credential exposure, or remote code execution. The skill's operations are confined to the local environment and focused on content generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 11:10 PM