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) usinggrepandhead(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
bashwith tools likegrep,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