syndly-setup
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external URLs (RSS feeds or sitemaps) provided by the user, creating a surface for indirect prompt injection where malicious content from the source could influence agent behavior. \n
- Ingestion points: The agent accepts a user-provided
urlduring theadd_sourceworkflow in SKILL.md. \n - Boundary markers: The instructions explicitly require the agent to show the exact input and receive explicit human approval before calling the
add_sourcetool and before writing local files. \n - Capability inventory: The agent has the ability to write to the local filesystem (
./.syndly/) and perform API publishing actions through theadd_sourcetool. \n - Sanitization: The instructions do not specify any validation or sanitization requirements for the content retrieved from or represented by the provided URLs.
Audit Metadata