skills/daxaur/openpaw/c-telegram/Gen Agent Trust Hub

c-telegram

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the processing of untrusted data from an external messaging platform (Telegram) which can influence agent behavior.
  • Ingestion points: Incoming Telegram messages are consumed via the OpenPaw bridge (SKILL.md).
  • Boundary markers: The documentation does not indicate the use of markers or delimiters to separate external messages from internal instructions.
  • Capability inventory: The bridge allows execution of all installed skills, which include functional capabilities like accessing email, managing calendars, and writing notes.
  • Sanitization: There is no evidence of sanitization or safety filtering applied to Telegram messages before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:44 AM
Security Audit — agent-trust-hub — c-telegram