Summarize
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions in
SKILL.mddirect the agent to invoke an external CLI tool namedsummarize. It provides multiple examples of executing this tool with shell arguments, including URLs, local file paths, and configuration flags. - [PROMPT_INJECTION]: The skill's core functionality involves processing and summarizing untrusted data from external sources, making it vulnerable to indirect prompt injection.
- Ingestion points: The agent is instructed to fetch and summarize data from arbitrary URLs, YouTube transcripts, and local files (e.g., PDF) as described in
SKILL.md. - Boundary markers: The prompt instructions do not include the use of delimiters or specific directives to the agent to ignore any malicious instructions that may be embedded within the content being summarized.
- Capability inventory: The skill possesses the capability to execute shell commands (the
summarizeutility) and potentially read local filesystem data. - Sanitization: There is no indication that the skill performs any sanitization, validation, or filtering of the external content before it is processed by the agent.
Audit Metadata