The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The script scripts/slop_score.py downloads linguistic resources, including stopwords and tokenizers, from the official NLTK repository. These are trusted resources required for the script's text analysis functionality.
[COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local Python script using the uv package manager to calculate text metrics. The script performs localized processing of text files provided as input.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted text content from users or external files.
Ingestion points: Text content provided by the user or read from files specified by the user in SKILL.md.
Boundary markers: No specific delimiters or "ignore instructions" markers are used when the agent processes the external text.
Capability inventory: The skill allows for local command execution (uv run) and file system modifications via smart_edit or write_file.
Sanitization: There is no evidence of sanitization or filtering to prevent embedded instructions in the input text from influencing the agent's behavior.

de-sloppify