skill-share
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user data (skill name and description) to generate structured files and Slack notifications.
- Ingestion points: Metadata fields provided during initialization are interpolated into
SKILL.mdand Slack block kit structures. - Boundary markers: No explicit instruction delimiters or boundary markers are defined to separate user content from system instructions in generated files.
- Capability inventory: The skill possesses file-write capabilities (directory/file creation) and network-egress capabilities via Slack integration tools (
SLACK_SEND_MESSAGE,SLACK_POST_MESSAGE_WITH_BLOCKS). - Sanitization: There is no evidence of validation or sanitization of user input before it is used in the Slack message payloads or file generation, which could lead to metadata poisoning or downstream formatting issues.
Audit Metadata