fragility-common
Shared library and file contracts for the fragility skills (system-history, bug-trace, refactor-plan, identify-fragile-systems, investigate-bug) and the findings scripts that file plans to the configured tracker (Jira or GitHub issues). Read when changing how those skills exchange data, or before running findings-doctor, findings-match, or findings-upsert.
88%
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 findings-match.ts fetches existing issue tickets from a tracker (GitHub or Jira) into findings.json, allowing outsiders to submit arbitrary free text via issues/comments that the agent subsequently ingests.
- Repository
BuilderIO/agent-native
- Revision
46ed84c
- 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.