creating-telegraph-pages

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill communicates with the well-known Telegraph API at https://api.telegra.ph.\n- [COMMAND_EXECUTION]: The agent executes a local Python helper script scripts/telegraph.py to process content and interact with the API.\n- [DATA_EXFILTRATION]: The skill transmits user-authorized content to the public Telegra.ph service. It includes mechanisms to redact sensitive access tokens from all program output.\n- [PROMPT_INJECTION]: The skill processes external text for publication, creating an indirect prompt injection surface. This is mitigated by strict instruction boundaries in the skill definition and a robust tag whitelist in the validation script.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 12:13 PM
Security Audit — agent-trust-hub — creating-telegraph-pages