ssotchk
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions direct the agent to aggregate and classify data from diverse external sources, including Slack channels, Jira tickets, Notion pages, and GitHub repositories. Because these sources can contain content authored by untrusted parties, they represent an attack surface for indirect prompt injection. The skill lacks instructions for the agent to use boundary markers or to ignore instructions embedded within the data being audited.
- Ingestion points: Reads content from files, READMEs, Notion, Slack, Jira, and GitHub.
- Boundary markers: None specified in the instructions to separate system instructions from analyzed data.
- Capability inventory: The skill is explicitly defined as read-only, which mitigates the risk of unauthorized actions, but the agent's response could still be manipulated.
- Sanitization: No filtering or sanitization of external content is mentioned before the agent processes it.
Audit Metadata