team-daily-report

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local script python3 ~/clawd/scripts/team_daily_report.py to process collected data and perform report distribution.
  • [PROMPT_INJECTION]: The skill contains an Indirect Prompt Injection surface (Category 8) due to its core functionality of summarizing log files.
  • Ingestion points: Processes data from untrusted or user-influenced files such as ~/clawd/memory/{YYYY-MM-DD}.md and ~/clawd/memory/learning-log.md.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the content of these logs as potentially hostile or to ignore embedded instructions.
  • Capability inventory: The system triggers local scripts that possess file system read access and network access (specifically for the Telegram Bot API and weather updates).
  • Sanitization: No sanitization or filtering logic is described for the log data before it is processed for the final report summary.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 06:09 PM
Security Audit — agent-trust-hub — team-daily-report