management-talk
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data retrieved from JIRA tickets, which could contain malicious instructions designed to influence the agent's behavior during the rewriting process.
- Ingestion points: The skill fetches ticket summaries and comments from JIRA using the
GET /rest/api/3/issue/<KEY>endpoint. - Boundary markers: The instructions do not specify the use of clear delimiters or warnings to ignore instructions embedded within the fetched JIRA data.
- Capability inventory: The skill has the ability to read and write to JIRA tickets (
POST /rest/api/3/issue/<KEY>/comment) and generates content intended for Slack, Email, and meeting talking points. - Sanitization: There is no explicit requirement for the agent to sanitize, escape, or validate the content retrieved from JIRA before processing it.
Audit Metadata