slack-network-alerts
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources and formats it for communication tools, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill ingests untrusted data from network device statuses (e.g., ping results, OSPF neighbor states, BGP peer info) and the outputs of other skills like
pyats-health-checkandpyats-security. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or treat embedded instructions within the ingested data as untrusted.
- Capability inventory: The skill utilizes Slack API capabilities including
chat:writefor posting messages,reactions:writefor emojis, andfiles:writefor uploading log excerpts and reports. - Sanitization: The instructions do not specify any sanitization, escaping, or filtering of the external network data before it is interpolated into the Slack Block Kit templates.
Audit Metadata