source-summarization
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a legitimate workflow for reading local markdown files (meta.md, transcript.md, content.md) and writing a summary (summary.md) based on user-approved drafts. All operations are confined to the local source folder.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the knowledge base, which could contain malicious instructions designed to influence the agent's summarization. \n
- Ingestion points: The agent reads transcript.md and content.md files within source folders (SKILL.md). \n
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the read content. \n
- Capability inventory: The skill allows the agent to write a summary.md file to the local directory (SKILL.md). \n
- Sanitization: The instructions do not prescribe sanitization or filtering for the external content before it is processed. \n
- Mitigation: The risk is mitigated by the mandatory interactive step where the agent must wait for user feedback and approval before proceeding to the next section or writing the final file.
Audit Metadata