daily-review

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes contents of user-managed markdown files (daily notes and task files) which presents an indirect prompt injection surface.
  • Ingestion points: Reads files from the daily/ and task/ directories as part of the review workflow.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" directives are defined for the file content processing in SKILL.md.
  • Capability inventory: The skill utilizes Bash, Write, and Edit tools to perform operations on the local file system and git repository.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the content read from the markdown files before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute git commands (git log, git diff, git commit) and grep to find task files. This is consistent with the skill's stated purpose of tracking developer activity and project status.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 06:48 AM
Security Audit — agent-trust-hub — daily-review