The Agent Skills Directory

[SAFE]: The skill is purely conceptual and instructional, based on the 'The Psychology of Human Misjudgment' chapter from Poor Charlie's Almanack. It provides cognitive behavioral frameworks for decision-making without implementing any executable scripts, binary files, or network operations.- [NO_CODE]: There are no executable scripts (.py, .js, .sh), binary files, or third-party dependencies associated with this skill. The analysis focuses entirely on the markdown instructions provided in SKILL.md and the test prompts in test-prompts.json.- [PROMPT_INJECTION]: No evidence of prompt injection or system prompt extraction attempts. The instructions focus on guiding the AI to assist users in identifying cognitive biases rather than bypassing safety filters.- [DATA_EXFILTRATION]: No network access or sensitive file access is requested or performed. The skill operates entirely within the context of the user interaction.- [INDIRECT_PROMPT_INJECTION]: While the skill processes user scenarios to identify biases (ingestion of untrusted data), it lacks high-privilege capabilities (file writes, network calls) that would make an ingestion-based attack viable. The risk is assessed as safe as the output is purely analytical and textual.

misjudgment-psychology-checklist