syndly-sources

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to the processing of external content.
  • Ingestion points: The agent retrieves data from external RSS feeds and sitemaps via the list_sources and list_recent_captures tool operations (found in SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters defined to separate external tool output from the agent's instructions, nor are there commands to ignore instructions embedded in the external data.
  • Capability inventory: The skill possesses write capabilities through the add_source, remove_source, and refresh_source tools, which could be targeted by a malicious feed.
  • Sanitization: The skill does not implement specific sanitization, filtering, or validation logic for the content retrieved from external sources before it is presented to the user or used in subsequent tool calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 08:24 AM
Security Audit — agent-trust-hub — syndly-sources