skills/andreadellacorte/groove/memory/Gen Agent Trust Hub

memory

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from external sources to generate summaries.
  • Ingestion points: Data is ingested in commands/log/daily.md (via git diff and task content), commands/log/git.md (via git log output), and in the weekly/monthly roll-up commands that read previously generated files.
  • Boundary markers: The instructions do not define clear delimiters or include warnings for the agent to ignore instructions that might be embedded within the git logs or task bodies being summarized.
  • Capability inventory: The skill possesses Read, Write, and Edit file permissions, along with the ability to execute system commands via Bash (including git, mkdir, and npx).
  • Sanitization: There is no evidence of sanitization, filtering, or escaping of the external content before it is processed by the LLM for report generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 12:28 PM