edge-candidate-agent
Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I. Use when users ask to turn hypotheses/anomalies into reproducible research tickets, convert validated ideas into `strategy.yaml` + `metadata.json`, or preflight-check interface compatibility (`edge-finder-candidate/v1`) before running pipeline backtests.
71
89%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The script `scripts/auto_detect_candidates.py` supports an optional `--llm-ideas-cmd` flag that executes an external command, passing market summary and anomalies as JSON to stdin, and reads back text hints. Because an outsider cannot directly push data into this command or stream, and the data consumed consists of local OHLCV parquet files and optional first-party files/CLI inputs rather than unmonitored external feeds, the risk is classified as low.
- Repository
- tradermonty/claude-trading-skills
- Commit
eab8d5c
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.