The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to record untrusted information into a persistent memory system without safety controls.
Ingestion points: The skill processes user requests and "significant discoveries" as data to be recorded (SKILL.md).
Boundary markers: No instructions for using delimiters or ignoring instructions within the ingested data are provided.
Capability inventory: The skill uses the write_memory tool to record data into the Serena long-term memory system.
Sanitization: No sanitization, escaping, or validation of the recorded content is specified.
[NO_CODE]: The skill consists exclusively of markdown instructions and does not include any executable scripts, binaries, or configuration for code execution.

memory-recorder