summarize
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses file reading and writing tools to process transcripts and save summaries to the local path
~/CybosVault/private/context/my-life/therapy/. These operations are consistent with the skill's stated purpose of managing personal therapy notes. - [PROMPT_INJECTION]: The skill processes untrusted content from transcript files, which represents a potential surface for indirect prompt injection.
- Ingestion points: Transcript content is read from user-provided file paths in
workflows/therapy.md. - Boundary markers: The workflow does not include explicit delimiters or instructions to the agent to ignore embedded commands within the transcript.
- Capability inventory: The skill utilizes file system tools (Read and Write).
- Sanitization: No sanitization or filtering of the transcript content is mentioned before processing.
- [SAFE]: No evidence of data exfiltration, credential harvesting, obfuscation, or remote code execution was found. The skill operates entirely within the local environment provided by the agent.
Audit Metadata