slack
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection because it allows the agent to ingest untrusted data from Slack messages.
- Ingestion points: The
readMessagesaction defined inSKILL.mdallows retrieval of message content from Slack channels. - Boundary markers: There are no boundary markers or instructions to treat external message content as untrusted data.
- Capability inventory: The skill includes high-impact capabilities such as
sendMessage,editMessage,deleteMessage, andpinMessage, which could be exploited if the agent follows malicious instructions found in messages. - Sanitization: The documentation does not specify any sanitization, filtering, or validation of incoming message content.
Audit Metadata