The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions and does not contain executable code, scripts, or system commands.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data such as platform moderation notices and user messages, which presents a surface for indirect prompt injection.
Ingestion points: SKILL.md (Section 1.1) instructs the agent to read external content, URLs, and messages.
Boundary markers: Absent; no delimiters are defined to separate instructions from untrusted data.
Capability inventory: The skill does not invoke tools, network operations, or file system writes.
Sanitization: Absent; no input filtering or escaping is specified.
[SAFE]: The skill's instructions are consistent with its stated purpose of assisting with legal compliance under the EU Digital Services Act. No obfuscation, prompt injection attempts, or malicious logic was identified.

plattform-dsa-art-14-eu-2022-2065