The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform a git synchronization operation by executing git -C <ceos_root> pull --ff-only --quiet 2>/dev/null. The target directory is dynamically determined by locating a .ceos marker file in the directory hierarchy.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it ingests and processes content from external markdown files.
Ingestion points: Evaluates data from data/people/, data/vision.md, and data/accountability.md.
Boundary markers: There are no defined delimiters or specific instructions to the agent to ignore embedded commands within the processed files.
Capability inventory: The skill utilizes Read, Write, and Glob tools and has the capability to execute shell commands via git.
Sanitization: The skill lacks explicit sanitization or validation mechanisms for content read from files before it is used to influence the agent's evaluation logic.

ceos-people