agent-device-evidence
Records iOS/Android native MP4 evidence for test/repro flows extracted from an Expensify GitHub PR or issue. Use when the user asks to "record the flow for PR
76
96%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly instructs the agent to "send the step text verbatim" and "pass explicit values verbatim" (so any API keys/passwords present in PR/issue steps would be included verbatim in generated scripts/commands) and also to surface parent errors verbatim, creating a direct secret-exfiltration risk.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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 required workflow fetches outsider-authored PR/issue bodies at runtime via `gh pr view ... --json title,body` / `gh issue view ... --json title,body,...`, then passes the extracted/possibly LLM-parsed steps and step text verbatim into the agent-device LLM driver (and uses the parsed flows preconditions), creating an indirect prompt-injection surface.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill requires a GitHub PR/issue URL (e.g. https://github.com/Expensify/App/pull/89475) which is fetched at runtime (via gh pr/issue view) and its body is passed to an LLM to parse and drive test steps, so external content directly controls prompts.
- Repository
- Expensify/App
- Commit
0498f1e
- 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.