file-todos
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands for file management and logging operations.
- Utilizes standard CLI tools including
ls,grep,sort,tail,awk,cp, andwcto manage todo items. - Executes a local shell script located at
./scripts/log-skill.shto log skill usage. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external markdown files, creating a surface for indirect prompt injection.
- Ingestion points: Reads and parses todo items from markdown files within the
todos/directory. - Boundary markers: The skill lacks explicit delimiters or instructions to the agent to ignore potentially malicious commands embedded within the todo file content.
- Capability inventory: The agent has the ability to read, write, and list files, as well as execute text-processing shell commands.
- Sanitization: There is no evidence of sanitization or validation performed on the content of the todo files before they are processed by the agent.
Audit Metadata