The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses python3 to execute a local utility script skills/shared/scripts/wordcount.py. This script is invoked to perform precise character counting and to validate if the condensed text meets the requested target length constraints. This is a controlled internal operation within the skill environment.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate summaries, which creates a surface for indirect prompt injection. 1. Ingestion points: Untrusted text enters the agent context via the text parameter in SKILL.md. 2. Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate the user-provided text from the skill's system instructions. 3. Capability inventory: The skill possesses the capability to execute local validation scripts and write summarized text to the outputs/ directory. 4. Sanitization: No input sanitization, filtering, or instruction detection is described in the skill workflow.
[EXTERNAL_DOWNLOADS]: The EASEL-META.md file contains several references to public GitHub repositories (e.g., praj2408/Text-Summarizer-Project). These links are provided for documentation and technical attribution purposes only; the skill does not attempt to download, install, or execute code from these external sources during operation.

text-condenser