project-management
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project trackers such as Jira, Linear, GitHub, and Trello. This creates a vulnerability surface where malicious instructions hidden in task descriptions or comments could influence the agent's behavior during processing.
- Ingestion points: External project management APIs (SKILL.md).
- Boundary markers: Absent; no explicit delimiters or instructions to ignore embedded content are defined for imported data.
- Capability inventory: Network requests to APIs for syncing and communication platforms (Slack/Teams) for posting updates.
- Sanitization: Absent; no mention of filtering, escaping, or validating external content before interpolation.
Audit Metadata