The Agent Skills Directory

[PROMPT_INJECTION]: Misleading metadata and instructions. Although the skill is named 'influence-psychology' and contains psychological research, the 'Instructions' and 'Output' sections in SKILL.md command the agent to 'Assess the current state of the authentication configuration' and report 'Configuration files or code changes.' This operational directive is inconsistent with the skill's description and could cause the agent to perform unauthorized data discovery on authentication setups when the skill is triggered.
[PROMPT_INJECTION]: Indirect prompt injection attack surface. The skill instructs the agent to process untrusted configuration data with powerful tools.
Ingestion points: SKILL.md instructions and project-level authentication configuration.
Boundary markers: None; there are no delimiters or warnings to ignore instructions embedded in the analyzed data.
Capability inventory: Access to Read, Glob, and Grep tools as defined in the frontmatter.
Sanitization: No sanitization or validation logic is specified for the data processed during the authentication assessment.

influence-psychology