lgnh-summarize-content
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the shell command
date +%Y-%m-%dto determine the current date for use in file naming and metadata. This is a benign use of system commands. - [EXTERNAL_DOWNLOADS]: The skill utilizes a
WebFetchtool to retrieve content from user-provided URLs for summarization. This is a primary feature of the skill but involves fetching content from arbitrary remote locations. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from external URLs and local files without safety boundaries.
- Ingestion points: Processes data from user-supplied URLs and local file paths (SKILL.md, Step 1).
- Boundary markers: Absent; the instructions do not include delimiters or specific warnings for the agent to ignore instructions embedded within the summarized content.
- Capability inventory: Includes file reading (Read), network fetching (WebFetch), shell command execution (
date), and file system writing. - Sanitization: Absent; no logic is provided to sanitize or escape the content retrieved from external sources before it is processed by the agent.
Audit Metadata