reports-client-status
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to collect and summarize project metadata from internal tools (Jira, Slack, Confluence, Fireflies). It follows the principle of least privilege by presenting the output to the user for review before any further action is taken.
- [DATA_EXFILTRATION]: While the skill accesses sensitive project information, all data processing remains within the agent's context. There are no network requests to unauthorized or external third-party domains. The instructions explicitly forbid automatic posting of collected data.
- [PROMPT_INJECTION]: The skill does not contain any instructions that attempt to override the underlying AI's safety guidelines or system prompts.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted content from external sources:
- Ingestion points: Data is pulled from Slack messages, Fireflies meeting summaries, and Jira ticket descriptions (referenced in SKILL.md).
- Boundary markers: The prompt lacks explicit delimiters or instructions to ignore potential commands embedded within the retrieved project data.
- Capability inventory: The skill's capabilities are limited to reading from specific tools (Slack, Jira, Fireflies, Confluence). It lacks dangerous capabilities like arbitrary command execution, file-system writes, or general network access.
- Sanitization: No explicit sanitization or filtering of the retrieved content is performed before summarization. The risk is mitigated by the requirement for human review of the final output.
Audit Metadata