file-reader
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands like
fileandtailto inspect file metadata and extract content from logs.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from local files without security delimiters. - Ingestion points: Untrusted content is ingested from local files via
read_fileand shell command output as defined in SKILL.md. - Boundary markers: The instructions lack markers or warnings to the agent to disregard instructions found within the files it reads.
- Capability inventory: The agent has the capability to read arbitrary text files and execute shell commands (
bash). - Sanitization: There is no evidence of sanitization or filtering of the file content before it is processed by the agent.
Audit Metadata