syndly-captures
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses defined tools (
list_sources,list_recent_captures) to fetch news data for the user. Its functionality is restricted to reading news content and presenting it. - [DATA_EXPOSURE]: The skill interacts with the local file system only to read and write a timestamp cursor in
.syndly/state/last-captures-check.txt. This is a standard practice for tracking state in information-retrieval skills and does not involve accessing sensitive user credentials or system configurations. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from news captures. While this constitutes an ingestion surface for untrusted content, the instructions are focused strictly on display (title, source, link), and the skill lacks dangerous capabilities (like shell execution or network exfiltration) that would make such an injection exploitable.
- Ingestion points:
list_recent_capturesoutput - Boundary markers: Absent
- Capability inventory: Restricted file write to
.syndly/state/last-captures-check.txt - Sanitization: Not explicitly defined in instructions, but risk is mitigated by limited agent capabilities.
Audit Metadata