The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell scripts for core functionality like document registration and portfolio syncing.
Evidence: Multiple invocations of bash targeting scripts such as source-registry.sh and sync-portfolio.sh located in a dynamically resolved plugin cache directory.
The skill uses a fallback resolution pattern: ${CLAUDE_PLUGIN_ROOT:-$(ls -td "$HOME"/.claude/plugins/cache/insight-wave/cogni-portfolio/*/ | head -1)} to locate its executable components.
[PROMPT_INJECTION]: The skill is designed to ingest and process data from untrusted external sources (uploaded documents), creating an attack surface for indirect prompt injection.
Ingestion points: The skill scans and reads .md, .docx, .pptx, .xlsx, and .pdf files from the project's uploads/ directory.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when interpolating extracted document content into the agent's context.
Capability inventory: The skill has access to the Bash tool for script execution, Write/Edit for file system modifications, and Read for data access.
Sanitization: There is no mention of sanitizing, escaping, or validating the extracted text from documents before it is used to populate entity fields or context entries.

portfolio-ingest