The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the 'available session' to update project documentation, creating an indirect prompt injection surface.
Ingestion points: The skill gathers data from 'user requirements, corrections and vetoes', 'failed approach', and 'session narrative' found in the interaction history (SKILL.md, Sections 1 and 2).
Boundary markers: The instructions do not specify the use of delimiters (like XML tags or triple quotes) when the agent processes or interpolates session data into the documentation templates.
Capability inventory: The agent is authorized to write to documentation files, modify AGENTS.md (via the agents-md-edit skill), and execute local maintenance scripts such as scripts/doc_nav_lint.py and scripts/audit.py (SKILL.md, Sections 3 and 4).
Sanitization: There are no explicit instructions for sanitizing or escaping the session data before it is persisted into the project's documentation files.

doc-update