session-archaeology
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes Python functions for reading session transcripts from specified file paths. This local file access is restricted to the intended purpose of parsing log data and does not perform any arbitrary command execution or system modification.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted session logs. It accurately identifies potential security risks associated with this data, such as the presence of API keys or PII, and includes a specific best practice recommendation to anonymize transcripts before analysis.
- [EXTERNAL_DOWNLOADS]: References to the author's GitHub repository ('itallstartedwithaidea/agent-skills') and website ('googleadsagent.ai') are provided for documentation and context. These are verified vendor resources consistent with the skill's authorship.
Audit Metadata