oncall-shift
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and parse untrusted text from handover notes and Slack conversations to create tracking documents and action plans.
- Ingestion points: The skill accepts raw text input via the
handover_notesparameter and processes Slack chat excerpts during the shift lifecycle as described in SKILL.md. - Boundary markers: The instructions do not specify any boundary markers or delimiters to isolate untrusted user content, nor do they instruct the agent to ignore potentially malicious instructions embedded in that content.
- Capability inventory: The skill can perform file system operations (creating and writing to markdown files in
~/.local/share/oncall-shifts/and writing the Slack handover to/tmp/handover-slack.txt) and interact with JIRA via MCP tools to create and edit issues. - Sanitization: No sanitization or validation steps are defined for the external text before it is interpolated into internal logs or external JIRA tickets.
Audit Metadata