The Agent Skills Directory

[NO_CODE] (SAFE): The skill consists entirely of Markdown instructions and examples. No Python or Node.js code is included, eliminating the risk of runtime malicious code execution.
[DATA_EXFILTRATION] (SAFE): No access to sensitive file paths (~/.ssh, ~/.aws) or unauthorized network commands was detected. Use of tools is limited to the defined 'WebSearch' and 'Read' for gathering public series information.
[PROMPT_INJECTION] (SAFE): The instructions are task-oriented and do not attempt to bypass safety filters, extract system prompts, or override agent constraints.
[INDIRECT_PROMPT_INJECTION] (SAFE): While the skill ingests untrusted data via WebSearch (Category 8 surface), the risk is minimal as the skill lacks high-impact capabilities such as file writing or arbitrary command execution.
Ingestion points: Ingests external series data, audience reviews, and hot discussions via the WebSearch tool.
Boundary markers: Absent; the instructions do not explicitly tell the agent to ignore instructions embedded in search results.
Capability inventory: Limited to WebSearch and Read tools. No exec, eval, or file-system write capabilities are present.
Sanitization: None detected; the skill relies on the underlying model's inherent guardrails.

series-analyzer