The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill enables the restoration of agent state, memory entries, and learning trajectories, which creates a surface where previously saved data is ingested into the agent context.
Ingestion points: The mcp__plugin_ruflo-core_ruflo__session_restore tool loads historical session data into the active agent environment (SKILL.md).
Boundary markers: The instructions do not specify any delimiters or explicit instructions for the agent to ignore potentially malicious content embedded within the restored session data.
Capability inventory: The skill is configured with access to the Bash tool in the frontmatter, which provides a high-privilege execution environment for any instructions that might be interpreted from the restored state.
Sanitization: There is no evidence of content validation, filtering, or sanitization performed on the restored session metrics or memory entries before they are processed by the agent.

session-persist