The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs local command execution during the 'Pre-Flight Check' step by running date '+%Y-%m-%d %H:%M' via Bash to generate timestamps for document metadata.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it systematically scans and processes untrusted data from multiple sources to build frameworks.
Ingestion points: The skill reads content from 02-personal/braindumps/, 03-professional/braindumps/, 04-projects/, 01-daily/briefs/, and 01-daily/checkins/.
Boundary markers: The instructions do not define clear delimiters or 'ignore' instructions when interpolating the contents of these documents into the synthesis prompts.
Capability inventory: The skill has the ability to create and update files in 05-knowledge/consolidated/, move files to 00-inbox/archive/, and execute shell commands.
Sanitization: There is no evidence of sanitization or validation of the ingested markdown content before it is used to generate new frameworks or update existing ones.

knowledge-consolidation