meeting-prep-cc

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates shell commands using participant names and company names provided by the user (e.g., grep -rl "$NAME\|$COMPANY" "$VAULT"). If these variables are not sanitized by the executing agent, they could serve as a vector for command injection.
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8).
  • Ingestion points: The skill reads markdown files (*.md) from a local directory (Obsidian vault) using grep and head (files: SKILL.md, SKILL-OC.md).
  • Boundary markers: No delimiters or instructions are used to tell the agent to ignore instructions embedded within the vault files.
  • Capability inventory: The agent has access to bash with tools like grep, find, xargs, sort, head, and the ability to write files to the local file system.
  • Sanitization: No sanitization or validation is performed on the content retrieved from the vault before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 11:04 PM