jbaruch/frequent-flyer-advocate
Write professional, persuasive complaint letters to US airlines emphasizing loyalty status, DOT regulations, and airline commitments.
89
94%
Does it follow best practices?
Impact
89%
1.17xAverage score across 10 eval scenarios
Advisory
Suggest reviewing before use
Security
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
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
Third-party content exposure detected (high risk: 0.75). The skill’s runtime LLM context can include **outsider-authored free text** from **public web content fetched at runtime** during Phase 3 “Dynamic Research” (via Playwright/WebFetch/WebSearch in `references/research-strategy.md`), which can ingest arbitrary page text into the agent before writing the letter.
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
Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires runtime fetching of external pages (e.g., FlightAware: https://www.flightaware.com/live/flight/[designator]/history/[YYYYMMDD] and DOT guidance: https://www.transportation.gov/airconsumer) to extract policy/flight-tracking quotes that are injected verbatim into complaint letters, so those remote resources directly control the agent's prompt/content generation.
- Audited
- Security analysis