Ae1
High
- Category
- analysis-evasion
- Content
| Cost of living | `cost.md` |
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
Buenos Aires
Security checks for vulnerabilities and agentic risk
Overview
This is a plain-text Buenos Aires guide with no code or persistence, but it gives under-cautioned legal, immigration, medical, and informal-currency advice that users should review carefully.
Install only if you want a static Buenos Aires reference guide and understand that it should not be treated as current legal, immigration, medical, tax, or financial advice. Verify visa status, emergency numbers, healthcare coverage, medication rules, exchange options, and any informal-market suggestions with official sources or qualified local professionals before acting.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (19)
Ae1
High
- Category
- analysis-evasion
- Content
| Cost of living | `cost.md` |
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Anti-Refusal Statement
High
- Category
- Anti-Refusal
- Content
- Ice cream (helado) - Crepes (panqueques) - Toast - Eaten from jar (don't judge) ### Best Dulce de Leche Products
- Confidence
- 85% confidence
- Finding
- Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
Vague Triggers
Medium
- Confidence
- 95% confidence
- Finding
- The trigger text says the skill should be used when a user asks about Buenos Aires 'for any purpose,' then lists a wide range of scenarios. That phrasing is expansive and lacks negative examples or clearer boundaries, which could cause unintended invocation on generic mentions of the city.
Missing User Warnings
Medium
- Confidence
- 95% confidence
- Finding
- This file gives specific healthcare guidance, emergency numbers, access expectations, medication availability, and cost/coverage information without warning that details may change and should be verified with current providers, hospitals, insurers, or emergency services. Users may rely on outdated or incomplete medical-system information during urgent or high-stakes situations, which can lead to delayed care, unexpected costs, or inappropriate care-seeking decisions.
Missing User Warnings
Medium
- Confidence
- 95% confidence
- Finding
- The guide explicitly recommends obtaining pesos through the informal 'blue rate'/'cueva' market but does not mention that this can involve illegality, counterfeit currency, theft, or scams. In a relocation guide aimed at residents, readers may treat the advice as endorsed and safe, increasing the chance they engage in risky in-person cash transactions.
Missing User Warnings
Medium
- Confidence
- 97% confidence
- Finding
- The text frames remote work on tourist status as a legal gray area with minimal enforcement, which normalizes conduct that may breach immigration or work-authorization requirements. Because this skill is specifically about visas and immigration, users are likely to treat the content as compliance advice, increasing the chance they engage in unauthorized work and face legal or immigration consequences.
Missing User Warnings
Medium
- Confidence
- 95% confidence
- Finding
- The document explicitly recommends visa runs, states people do them for years, and says travelers can return immediately, while downplaying enforcement and not clearly warning that border officials may deny entry or view this as misuse of tourist status. In a travel/relocation skill, readers may rely on this as practical compliance guidance, which can lead to immigration violations, refusal of entry, fines, or future residency problems.
Natural-Language Policy Violations
Low
- Confidence
- 88% confidence
- Finding
- The phrase 'Spanish requirement' presents Spanish as a requirement and does not offer any user choice or contextual opt-in. This can be read as a locale/language policy constraint expressed in natural language rather than a user-selectable preference.
Natural-Language Policy Violations
Low
- Confidence
- 78% confidence
- Finding
- The phrase 'extremely affordable for dollar earners' frames the guidance around a specific currency/user locale perspective rather than neutrally serving a broad audience. While not severe, this is a natural-language locale bias that could conflict with a policy requiring language or locale neutrality unless explicitly scoped.
Natural-Language Policy Violations
Low
- Confidence
- 80% confidence
- Finding
- This is a natural-language policy concern because it encodes a sweeping identity claim about a population rather than neutrally describing a possible perspective. Such phrasing can reinforce stereotypes and present a contested cultural framing as universal guidance.
Natural-Language Policy Violations
Low
- Confidence
- 79% confidence
- Finding
- The document states 'Spanish only' for public schools, which imposes a specific language expectation in the skill content without any user opt-in or framing that the skill is specifically for Spanish-speaking users. Because this skill is a general education guide, the repeated language constraint could be interpreted as a locale-policy issue under the rule for forced language without choice.
Natural-Language Policy Violations
Low
- Confidence
- 88% confidence
- Finding
- The guidance says '"Sin carne" might still include chicken or fish in local understanding,' which assumes use of Spanish-language phrasing without offering an English alternative or noting that language choice is optional. Under the policy, forcing or presuming a specific language/locale without opt-in can be a natural-language policy concern.
Natural-Language Policy Violations
Low
- Confidence
- 80% confidence
- Finding
- The phrase "Slow by US standards" frames service expectations around a specific national baseline. This is a natural-language locale assumption in a general guide and does not offer an alternative or opt-in for users from other locales.
Natural-Language Policy Violations
Low
- Confidence
- 77% confidence
- Finding
- SQP-3 applies to all file types and includes language or locale policy violations. This file is written solely for a specific locale and audience ('Buenos Aires Expat Lifestyle Guide') with no indication that users can choose a different language or locale framing, which may conflict with policies requiring user opt-in for locale-specific guidance.
Natural-Language Policy Violations
Low
- Confidence
- 78% confidence
- Finding
- The phrase "English-speaking" appears as a preferred filter for finding doctors, which embeds an English-language assumption in the guidance. Under the language/locale policy, natural-language content should avoid forcing or privileging a specific language without user opt-in or clear justification.
Natural-Language Policy Violations
Low
- Confidence
- 85% confidence
- Finding
- The document includes locale-specific language such as "Subte" and elsewhere uses terms like "verduleria," "milonga," and "porteno" as part of its guidance without giving the user an explicit language or terminology choice. Under the policy rule, forcing a specific language or locale without opt-in can be a natural-language policy issue even in otherwise informative content.
Natural-Language Policy Violations
Low
- Confidence
- 79% confidence
- Finding
- The file is entirely written in English while instructing users about Spanish-speaking neighborhoods and local practices, and it uses imperative guidance without any indication that language can be adapted to user preference. Under the stated policy, a skill that effectively fixes a specific language without opt-in can be a locale-policy concern.
Natural-Language Policy Violations
Low
- Confidence
- 77% confidence
- Finding
- This markdown file is natural-language guidance for travelers in Buenos Aires, but it presents all instructions and safety advice exclusively in English. Under the stated policy, forcing a specific language without user opt-in can be a locale or language policy violation unless the constraint is explicitly documented and justified.
Static analysis
No suspicious patterns detected.