conversation-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of chat transcripts or conversation exports as specified in
references/full-prompt.md. While it provides detailed formatting and analysis instructions, it lacks specific security measures to prevent instructions inside the transcripts from influencing agent behavior. - Ingestion points: The skill accepts transcript data as its primary input (
SKILL.md,references/full-prompt.md). - Boundary markers: Absent. There are no defined delimiters (e.g., XML tags or unique markers) or specific instructions to the agent to treat the input data as non-executable text.
- Capability inventory: The skill instructions do not define specific dangerous tools or script executions, inheriting the base capabilities of the host agent environment.
- Sanitization: Absent. The instructions do not specify any filtering or escaping of content found within the provided transcripts.
Audit Metadata