The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands like curl to interact with a local notification service at http://localhost:31337/notify and fabric -y for processing YouTube transcripts.
[DATA_EXFILTRATION]: Execution metadata, including workflow names and timestamps, is appended to a local storage file at ~/.claude/LIFEOS/MEMORY/SKILLS/execution.jsonl.
[PROMPT_INJECTION]: The skill ingests untrusted data from external sources, creating a surface for indirect prompt injection. Ingestion points: The FindAphorism workflow uses WebFetch to retrieve content from user-provided URLs. Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are defined for the fetched content. Capability inventory: The agent can modify local files using the Edit tool and execute shell commands via curl and echo. Sanitization: The skill does not describe specific sanitization or filtering steps for content retrieved from external sources before it is analyzed.

Aphorisms