The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell commands to initialize its directory structure. Specifically, it executes mkdir -p to create the ara/ directory hierarchy for storing research artifacts. This is a standard initialization procedure for its stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes the entire conversation history to extract research-significant events, creating an attack surface where malicious instructions in the conversation could influence the recording process.
Ingestion points: Reads the full conversation history to identify decisions, experiments, and claims (SKILL.md, Procedure step 2).
Boundary markers: Absent; the skill does not use specific delimiters to isolate conversation content from its own processing instructions.
Capability inventory: The skill has the ability to execute shell commands (mkdir) and perform file system writes and appends across multiple directories (SKILL.md, Initialization and Writing Formats).
Sanitization: The skill does not explicitly sanitize or validate the content extracted from the conversation before writing it to YAML and Markdown files, though it does use a provenance tagging system to label the source of information.

ara-research-manager