readability-analysis
Warn
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The instructions require the execution of a Python script located at
scripts/report_publish.py. Because this script is not part of the provided skill package, its contents and safety cannot be verified. - [INDIRECT_PROMPT_INJECTION]: The skill fetches untrusted data from external sources and incorporates it into a report that is subsequently processed by a shell command. This creates a vulnerability surface where malicious content could influence the agent's actions or the script's behavior.
- Ingestion points: External content retrieved from URLs via the
webfetchtool. - Boundary markers: No delimiters or safety instructions are defined to separate user-provided content from the skill's operational logic.
- Capability inventory: Writing local markdown files and executing a Python script via the command line.
- Sanitization: The process does not describe any sanitization, filtering, or validation of the fetched text before it is processed and passed to the publishing script.
Audit Metadata